Search

Fetal brain tissue segmentation in magnetic resonance imaging (MRI) is a crucial tool that supports the understanding of neurodevelopment, yet it faces challenges due to the heterogeneity of data coming from different scanners and settings, and due to data scarcity. Recent approaches based on domain randomization, like SynthSeg, have shown a great potential for single source domain generalization, by simulating images with randomized contrast and image resolution from the label maps. In this work, we investigate how to maximize the out-of-domain (OOD) generalization potential of SynthSeg-based methods in fetal brain MRI. Specifically, when studying data generation, we demonstrate that the simple Gaussian mixture models used in SynthSeg enable more robust OOD generalization than physics-informed generation methods. We also investigate how intensity clustering can help create more faithful synthetic images, and observe that it is key to achieving a non-trivial OOD generalization capability when few label classes are available. Finally, by combining for the first time SynthSeg with modern fine-tuning approaches based on weight averaging, we show that fine-tuning a model pre-trained on synthetic data on a few real image-segmentation pairs in a new domain can lead to improvements in the target domain, but also in other domains. We summarize our findings as five key recommendations that we believe can guide practitioners who would like to develop SynthSeg-based approaches in other organs or modalities.

There is a history of simple forecast error growth models designed to capture the key properties of error growth in operational numerical weather prediction (NWP) models. We propose here such a scalar model that relies on the previous ones and incorporates multiplicative noise in a nonlinear stochastic differential equation (SDE). We analyze the properties of the SDE, including the shape of the error growth curve for small times and its stationary distribution, and prove well-posedness and positivity of solutions. We then fit this model to operational NWP error growth curves, showing good agreement with both the mean and probabilistic features of the error growth. These results suggest that the dynamic-stochastic error growth model proposed herein and similar ones could play a role in many other areas of the sciences that involve prediction., Comment: 10 pages, 7 figures

In this paper, we derive variational inference upper-bounds on the log-partition function of pairwise Markov random fields on the Boolean hypercube, based on quantum relaxations of the Kullback-Leibler divergence. We then propose an efficient algorithm to compute these bounds based on primal-dual optimization. An improvement of these bounds through the use of ''hierarchies,'' similar to sum-of-squares (SoS) hierarchies is proposed, and we present a greedy algorithm to select among these relaxations. We carry extensive numerical experiments and compare with state-of-the-art methods for this inference problem.

The advancement of the Event Horizon Telescope has enabled the study of relativistic jets in active galactic nuclei down to sub-parsec linear scales even at high redshift. Quasi-simultaneous multifrequency observations provide insights into the physical conditions in compact regions and allow testing accretion theories. Initially we aimed at measuring the magnetic field strength close to the central supermassive black hole in NRAO 530 (1730-130) by studying frequency-dependent opacity of the jet matter, Faraday rotation and the spectral index in the mm-radio bands. NRAO 530 was observed quasi-simultaneously at 15, 22, 43, 86, and 227 GHz at four different very long baseline interferometer (VLBI) networks. By the means of imaging and model-fitting, we aligned the images, taken at different frequencies. We explored opacity along the jet and distribution of the linearly polarized emission in it. Our findings reveal that the jet of NRAO 530 at 86 and 227 GHz is transparent down to its origin, with 70 mJy emission detected at 227 GHz potentially originating from the accretion disk. The magnetic field strength near the black hole, estimated at $5r_\mathrm{g}$, is $3\times10^3-3\times10^4$ G (depending on the central black hole mass). These values represent some of the highest magnetic field strengths reported for active galaxies. We also report the first ever VLBI measurement of the Faraday rotation at 43-227 GHz, which reveals rotation measure values as high as -48000 rad/m2 consistent with higher particle density and stronger magnetic fields at the jet's outset. The complex shape of the jet in NRAO 530 is in line with the expected behavior of a precessing jet, with a period estimated to be around $6\pm4$~years., Comment: 18 pages, accepted to A&A

Direct Z-scheme heterostructures with enhanced redox potential are increasingly regarded as promising materials for solar-driven water splitting. This potential arises from the synergistic interaction between the intrinsic dipoles in Janus materials and the interfacial electric fields across the layers. In this study, we explore the photocatalytic potential of 20 two-dimensional (2D) Janus transition metal dichalcogenide (TMDC) heterobilayers for efficient water splitting. Utilizing density functional theory (DFT) calculations, we first screen these materials based on key properties such as band gaps and the magnitude of intrinsic electric fields to identify promising candidates. We then evaluate additional critical factors, including carrier mobility and surface chemical reactions, to fully assess their performance. The intrinsic dipole moments in Janus materials generate built-in electric fields that enhance charge separation and reduce carrier recombination, thereby improving photocatalytic efficiency. Furthermore, we employ the Fr\"{o}hlich interaction model to quantify the mobility contributions from the longitudinal optical phonon mode, providing detailed insights into how carrier mobility, influenced by phonon scattering, affects photocatalytic performance. Our results reveal that several Janus-TMDC heterobilayers, including WSe$_2$-SWSe, WSe$_2$-TeWSe, and WS$_2$-SMoSe, exhibit strong absorption in the visible spectrum and achieve solar-to-hydrogen (STH) conversion efficiencies of up to 33.24%. These findings demonstrate the potential of Janus-based Z-scheme systems to overcome existing limitations in photocatalytic water splitting by optimizing the electronic and structural properties of 2D materials. This research highlights a viable pathway for advancing clean energy generation through enhanced photocatalytic processes., Comment: 30 pages, 6 figures, 4 tables

Pre-training is notoriously compute-intensive and academic researchers are notoriously under-resourced. It is, therefore, commonly assumed that academics can't pre-train models. In this paper, we seek to clarify this assumption. We first survey academic researchers to learn about their available compute and then empirically measure the time to replicate models on such resources. We introduce a benchmark to measure the time to pre-train models on given GPUs and also identify ideal settings for maximizing training speed. We run our benchmark on a range of models and academic GPUs, spending 2,000 GPU-hours on our experiments. Our results reveal a brighter picture for academic pre-training: for example, although Pythia-1B was originally trained on 64 GPUs for 3 days, we find it is also possible to replicate this model (with the same hyper-parameters) in 3x fewer GPU-days: i.e. on 4 GPUs in 18 days. We conclude with a cost-benefit analysis to help clarify the trade-offs between price and pre-training time. We believe our benchmark will help academic researchers conduct experiments that require training larger models on more data. We fully release our codebase at: https://github.com/apoorvkh/academic-pretraining.

Bayesian optimization devolves the global optimization of a costly objective function to the global optimization of a sequence of acquisition functions. This inner-loop optimization can be catastrophically difficult if it involves posterior samples, especially in higher dimensions. We introduce an efficient global optimization strategy for posterior samples based on global rootfinding. It provides gradient-based optimizers with judiciously selected starting points, designed to combine exploitation and exploration. The algorithm scales practically linearly to high dimensions. For posterior sample-based acquisition functions such as Gaussian process Thompson sampling (GP-TS) and variants of entropy search, we demonstrate remarkable improvement in both inner- and outer-loop optimization, surprisingly outperforming alternatives like EI and GP-UCB in most cases. We also propose a sample-average formulation of GP-TS, which has a parameter to explicitly control exploitation and can be computed at the cost of one posterior sample. Our implementation is available at https://github.com/UQUH/TSRoots .

Warm Saturn type exoplanets orbiting M-dwarfs are particularly suitable for in-depth cloud characterisation through transmission spectroscopy due to their favourable stellar to planetary radius contrast. However, modelling cloud formation consistently within the 3D atmosphere remains computationally challenging. The aim is to explore the combined atmospheric and micro-physical cloud structure, and the kinetic gas-phase chemistry for the warm Saturn HATS0-6b orbiting an M-dwarf. A combined 3D cloudy atmosphere model is constructed by iteratively executing the 3D General Circulation Model (GCM) expeRT/MITgcm and a kinetic cloud formation model, each in its full complexity. Resulting cloud particle number densities, sizes, and compositions are used to derive the local cloud opacity which is then utilised in the next GCM iteration. The disequilibrium H/C/O/N gas-phase chemistry is calculated for each iteration to assess the resulting transmission spectrum in post-processing. The cloud opacity feedback causes a temperature inversion at the sub-stellar point and at the evening terminator at gas pressures higher than 0.01 bar. Furthermore, clouds cool the atmosphere between 0.01 bar and 10 bar, and narrow the equatorial wind jet. The transmission spectrum shows muted gas-phase absorption and a cloud particle silicate feature at approximately 10 micron. The combined atmosphere-cloud model retains the full physical complexity of each component and therefore enables a detailed physical interpretation with JWST NIRSpec and MIRI LRS observational accuracy. The model shows that warm Saturn type exoplanets around M-dwarfs are ideal candidates to search for limb asymmetries in clouds and chemistry, identify cloud particle composition by observing their spectral features, and identify the cloud-induced strong thermal inversion that arises on these planets specifically., Comment: 21 pages, 15 figures, Accepted by A&A

In this paper, we first show that increases in beam size of even just small-sized LLM (1B-7B parameters) require an extensive GPU resource consumption, leading to up to 80% of recurring crashes due to memory overloads in LLM-based APR. Seemingly simple solutions to reduce memory consumption are (1) to quantize LLM models, i.e., converting the weights of a LLM from high-precision values to lower-precision ones. and (2) to make beam search sequential, i.e., forwarding each beam through the model sequentially and then concatenate them back into a single model output. However, we show that these approaches still do not work via both theoretical analysis and experiments. To address this, we introduce FLAMES, a novel LLM-based APR technique that employs semantic-guided patch generation to enhance repair effectiveness and memory efficiency. Unlike conventional methods that rely on beam search, FLAMES utilizes greedy decoding to enhance memory efficiency while steering the search to more potentially good repair candidates via a semantic-guided best-first search algorithm. At each decoding step, FLAMES uses semantic feedback from test validation such as the number of passing and failing test cases to select the most promising token to explore further. Our empirical evaluation on the Defects4J and HumanEval-Java datasets shows that FLAMES not only substantially reduces memory consumption by up to 83% compared to conventional LLM-based APR, but also accelerates the repair process. Remarkably, FLAMES successfully generated 133 and 103 correct fixes for 333 and 163 bugs in the Defects4J and HumanEval-Java datasets, respectively. This suggests that FLAMES is not only more efficient but also outperforms state-of-the-art techniques, fixing at least 10 and 11 more bugs than SOTA baselines in the Defects4J and HumanEval-Java datasets, respectively.

Understanding events in time series is an important task in a variety of contexts. However, human analysis and labeling are expensive and time-consuming. Therefore, it is advantageous to learn embeddings for moments in time series in an unsupervised way, which allows for good performance in classification or detection tasks after later minimal human labeling. In this paper, we propose dynamic contrastive learning (DynaCL), an unsupervised contrastive representation learning framework for time series that uses temporal adjacent steps to define positive pairs. DynaCL adopts N-pair loss to dynamically treat all samples in a batch as positive or negative pairs, enabling efficient training and addressing the challenges of complicated sampling of positives. We demonstrate that DynaCL embeds instances from time series into semantically meaningful clusters, which allows superior performance on downstream tasks on a variety of public time series datasets. Our findings also reveal that high scores on unsupervised clustering metrics do not guarantee that the representations are useful in downstream tasks.

Large Language Models (LLMs) have revolutionized natural language processing, but their application to speech-based tasks remains challenging due to the complexities of integrating audio and text modalities. This paper introduces Ichigo, a mixed-modal model that seamlessly processes interleaved sequences of speech and text. Utilizing a tokenized early-fusion approach, Ichigo quantizes speech into discrete tokens and employs a uniform transformer-based architecture for both speech and text modalities. This method enables joint reasoning and generation across modalities without the need for separate adapters. We present a comprehensive training methodology, including pre-training on multilingual speech recognition datasets and fine-tuning on a curated instruction dataset. Ichigo demonstrates state-of-the-art performance on speech question-answering benchmarks, outperforming existing open-source speech language models and achieving comparable results to cascaded systems. Notably, Ichigo exhibits a latency of just 111 ms to first token generation, significantly lower than current models. Our approach not only advances the field of multimodal AI but also provides a framework for smaller research teams to contribute effectively to open-source speech-language models.

Free-stream preservation is an essential property for numerical solvers on curvilinear grids. Key to this property is that the metric terms of the curvilinear mapping satisfy discrete metric identities, i.e., have zero divergence. Divergence-free metric terms are furthermore essential for entropy stability on curvilinear grids. We present a new way to compute the metric terms for discontinuous Galerkin spectral element methods (DGSEMs) that guarantees they are divergence-free. Our proposed mimetic approach uses projections that fit within the de Rham Cohomology.

Adversarial training can be used to learn models that are robust against perturbations. For linear models, it can be formulated as a convex optimization problem. Compared to methods proposed in the context of deep learning, leveraging the optimization structure allows significantly faster convergence rates. Still, the use of generic convex solvers can be inefficient for large-scale problems. Here, we propose tailored optimization algorithms for the adversarial training of linear models, which render large-scale regression and classification problems more tractable. For regression problems, we propose a family of solvers based on iterative ridge regression and, for classification, a family of solvers based on projected gradient descent. The methods are based on extended variable reformulations of the original problem. We illustrate their efficiency in numerical examples.

Linear temporal logic (LTL) and, more generally, $\omega$-regular objectives are alternatives to the traditional discount sum and average reward objectives in reinforcement learning (RL), offering the advantage of greater comprehensibility and hence explainability. In this work, we study the relationship between these objectives. Our main result is that each RL problem for $\omega$-regular objectives can be reduced to a limit-average reward problem in an optimality-preserving fashion, via (finite-memory) reward machines. Furthermore, we demonstrate the efficacy of this approach by showing that optimal policies for limit-average problems can be found asymptotically by solving a sequence of discount-sum problems approximately. Consequently, we resolve an open problem: optimal policies for LTL and $\omega$-regular objectives can be learned asymptotically.

Without trust, patients may hesitate to engage with AI systems, significantly limiting the technology's potential in mental healthcare. This paper focuses specifically on the trust that mental health patients, as direct users, must have in AI systems, highlighting the most sensitive and direct relationship between AI systems and those whose mental healthcare is impacted by them. We explore the concept of justified trust, why it is important for patient positive care outcomes, and the strategies needed to foster and maintain this trust. By examining these aspects, we highlight how cultivating justified trust is key to unlocking AI's potential impact in mental healthcare., Comment: Both authors have contributed equally to this work. Submitted to Frontiers in Human Dynamics

The aim of these notes is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimilation. The perspective is one that is primarily aimed at researchers from inverse problems and/or data assimilation who wish to see a mathematical presentation of machine learning as it pertains to their fields. As a by-product, we include a succinct mathematical treatment of various topics in machine learning., Comment: 254 pages

We demonstrate efficient in-plane optical fiber collection of single photon emission from quantum dots embedded in photonic crystal cavities. This was achieved via adiabatic coupling between a tapered optical fiber and a tapered on-chip photonic waveguide coupled to the photonic crystal cavity. The collection efficiency of a dot in a photonic crystal cavity was measured to be 5 times greater via the tapered optical fiber compared to collection by a microscope objective lens above the cavity. The single photon source was also characterized by second order photon correlations measurements giving g(2)(0)=0.17 under non-resonant excitation. Numerical calculations demonstrate that the collection efficiency could be further increased by improving the dot-cavity coupling and by increasing the overlap length of the tapered fiber with the on-chip waveguide. An adiabatic coupling of near unity is predicted for an overlap length of 5 microns., Comment: 22 pages, 12 figures

Thompson sampling (TS) is a simple, effective stochastic policy in Bayesian decision making. It samples the posterior belief about the reward profile and optimizes the sample to obtain a candidate decision. In continuous optimization, the posterior of the objective function is often a Gaussian process (GP), whose sample paths have numerous local optima, making their global optimization challenging. In this work, we introduce an efficient global optimization strategy for GP-TS that carefully selects starting points for gradient-based multi-start optimizers. It identifies all local optima of the prior sample via univariate global rootfinding, and optimizes the posterior sample using a differentiable, decoupled representation. We demonstrate remarkable improvement in the global optimization of GP posterior samples, especially in high dimensions. This leads to dramatic improvements in the overall performance of Bayesian optimization using GP-TS acquisition functions, surprisingly outperforming alternatives like GP-UCB and EI., Comment: Paper accepted at the NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty for an oral presentation

The first very long baseline interferometry (VLBI) detections at 870$\mu$m wavelength (345$\,$GHz frequency) are reported, achieving the highest diffraction-limited angular resolution yet obtained from the surface of the Earth, and the highest-frequency example of the VLBI technique to date. These include strong detections for multiple sources observed on inter-continental baselines between telescopes in Chile, Hawaii, and Spain, obtained during observations in October 2018. The longest-baseline detections approach 11$\,$G$\lambda$ corresponding to an angular resolution, or fringe spacing, of 19$\mu$as. The Allan deviation of the visibility phase at 870$\mu$m is comparable to that at 1.3$\,$mm on the relevant integration time scales between 2 and 100$\,$s. The detections confirm that the sensitivity and signal chain stability of stations in the Event Horizon Telescope (EHT) array are suitable for VLBI observations at 870$\mu$m. Operation at this short wavelength, combined with anticipated enhancements of the EHT, will lead to a unique high angular resolution instrument for black hole studies, capable of resolving the event horizons of supermassive black holes in both space and time., Comment: Corresponding author: S. Doeleman

In this work, we propose a mean-squared error-based risk that enables the comparison and optimization of estimators of squared calibration errors in practical settings. Improving the calibration of classifiers is crucial for enhancing the trustworthiness and interpretability of machine learning models, especially in sensitive decision-making scenarios. Although various calibration (error) estimators exist in the current literature, there is a lack of guidance on selecting the appropriate estimator and tuning its hyperparameters. By leveraging the bilinear structure of squared calibration errors, we reformulate calibration estimation as a regression problem with independent and identically distributed (i.i.d.) input pairs. This reformulation allows us to quantify the performance of different estimators even for the most challenging calibration criterion, known as canonical calibration. Our approach advocates for a training-validation-testing pipeline when estimating a calibration error on an evaluation dataset. We demonstrate the effectiveness of our pipeline by optimizing existing calibration estimators and comparing them with novel kernel ridge regression-based estimators on standard image classification tasks., Comment: Preprint

The objective of the study is to evaluate the evolution of the performance of the new ATLAS Inner-Tracker (ITk) strip sensors as a function of radiation exposure, to ensure the proper operation of the upgraded detector during the lifetime of the High-Luminosity Large Hadron Collider (HL-LHC). Full-size ATLAS ITk Barrel Short-Strip (SS) sensors with final layout design, ATLAS18SS, have been irradiated with neutrons and gammas, to confirm the results obtained with prototypes and miniature sensors during the development phase. The irradiations cover a wide range of fluences and doses that ITk will experience, going from 1e13 neq/cm2 and 0.49 Mrad, to 1.6e15 neq/cm2 and 80 Mrad. The split irradiation enables a proper combination of fluence and dose values of the HL-LHC, including a 1.5 safety factor. A complete electrical characterization of the key sensor parameters before and after irradiation is presented, studying the leakage current, bulk capacitance, single-strip and inter-strip characteristics. The results confirm the fulfilment of the ATLAS specifications throughout the whole experiment. The study of a wide range of fluences and doses also allows to obtain detailed results, such as the frequency dependence of the bulk capacitance measurements for highly irradiated sensors, or the evolution of the punch-through protection and inter-strip resistance with radiation., Comment: 25th International Workshop on Radiation Imaging Detectors (iWoRiD2024), Lisbon June 30th - July 4th 2024

Clinnova, a collaborative initiative involving France, Germany, Switzerland, and Luxembourg, is dedicated to unlocking the power of precision medicine through data federation, standardization, and interoperability. This European Greater Region initiative seeks to create an interoperable European standard using artificial intelligence (AI) and data science to enhance healthcare outcomes and efficiency. Key components include multidisciplinary research centers, a federated biobanking strategy, a digital health innovation platform, and a federated AI strategy. It targets inflammatory bowel disease, rheumatoid diseases, and multiple sclerosis (MS), emphasizing data quality to develop AI algorithms for personalized treatment and translational research. The IHU Strasbourg (Institute of Minimal-invasive Surgery) has the lead in this initiative to develop the federated learning (FL) proof of concept (POC) that will serve as a foundation for advancing AI in healthcare. At its core, Clinnova-MS aims to enhance MS patient care by using FL to develop more accurate models that detect disease progression, guide interventions, and validate digital biomarkers across multiple sites. This technical report presents insights and key takeaways from the first cross-border federated POC on MS segmentation of MRI images within the Clinnova framework. While our work marks a significant milestone in advancing MS segmentation through cross-border collaboration, it also underscores the importance of addressing technical, logistical, and ethical considerations to realize the full potential of FL in healthcare settings.

Underwater vision is crucial for autonomous underwater vehicles (AUVs), and enhancing degraded underwater images in real-time on a resource-constrained AUV is a key challenge due to factors like light absorption and scattering, or the sufficient model computational complexity to resolve such factors. Traditional image enhancement techniques lack adaptability to varying underwater conditions, while learning-based methods, particularly those using convolutional neural networks (CNNs) and generative adversarial networks (GANs), offer more robust solutions but face limitations such as inadequate enhancement, unstable training, or mode collapse. Denoising diffusion probabilistic models (DDPMs) have emerged as a state-of-the-art approach in image-to-image tasks but require intensive computational complexity to achieve the desired underwater image enhancement (UIE) using the recent UW-DDPM solution. To address these challenges, this paper introduces UW-DiffPhys, a novel physical-based and diffusion-based UIE approach. UW-DiffPhys combines light-computation physical-based UIE network components with a denoising U-Net to replace the computationally intensive distribution transformation U-Net in the existing UW-DDPM framework, reducing complexity while maintaining performance. Additionally, the Denoising Diffusion Implicit Model (DDIM) is employed to accelerate the inference process through non-Markovian sampling. Experimental results demonstrate that UW-DiffPhys achieved a substantial reduction in computational complexity and inference time compared to UW-DDPM, with competitive performance in key metrics such as PSNR, SSIM, UCIQE, and an improvement in the overall underwater image quality UIQM metric. The implementation code can be found at the following repository: https://github.com/bachzz/UW-DiffPhys

There is a well-established dictionary between zonotopes, hyperplane arrangements, and their (oriented) matroids. Arguably one of the most famous examples is the class of graphical zonotopes, also called acyclotopes, which encode subzonotopes of the type-A root polytope, the permutahedron. Stanley (1991) gave a general interpretation of the coefficients of the Ehrhart polynomial (integer-point counting function for a polytope) of a zonotope via linearly independent subsets of its generators. Applying this to the graphical case shows that Ehrhart coefficients count induced forests of the graph of fixed sizes. Our first goal is to extend and popularize this story to other root systems, which on the combinatorial side is encoded by signed graphs analogously to the work by Greene and Zaslavsky (1983). We compute the Ehrhart polynomial of the acyclotope in the signed case, and we give a matroid-dual construction, giving rise to tocyclotopes, and compute their Ehrhart polynomials. Applying the same duality construction to a general integral matrix gives rise to a lattice Gale zonotope, whose face structure was studies by McMullen (1971) and whose duality nature is a special instance of D'Adderio--Moci's arithmetic matroids. We describe its Ehrhart polynomials in terms of the given matrix., Comment: 18 pages, 2 figures

Multilingual automatic speech recognition (ASR) in the medical domain serves as a foundational task for various downstream applications such as speech translation, spoken language understanding, and voice-activated assistants. This technology enhances patient care by enabling efficient communication across language barriers, alleviating specialized workforce shortages, and facilitating improved diagnosis and treatment, particularly during pandemics. In this work, we introduce MultiMed, a collection of small-to-large end-to-end ASR models for the medical domain, spanning five languages: Vietnamese, English, German, French, and Mandarin Chinese, together with the corresponding real-world ASR dataset. To our best knowledge, MultiMed stands as the largest and the first multilingual medical ASR dataset, in terms of total duration, number of speakers, diversity of diseases, recording conditions, speaker roles, unique medical terms, accents, and ICD-10 codes. Secondly, we establish the empirical baselines, present the first reproducible study of multilinguality in medical ASR, conduct a layer-wise ablation study for end-to-end ASR training, and provide the first linguistic analysis for multilingual medical ASR. All code, data, and models are available online https://github.com/leduckhai/MultiMed/tree/master/MultiMed, Comment: Preprint

Physics-informed machine learning typically integrates physical priors into the learning process by minimizing a loss function that includes both a data-driven term and a partial differential equation (PDE) regularization. Building on the formulation of the problem as a kernel regression task, we use Fourier methods to approximate the associated kernel, and propose a tractable estimator that minimizes the physics-informed risk function. We refer to this approach as physics-informed kernel learning (PIKL). This framework provides theoretical guarantees, enabling the quantification of the physical prior's impact on convergence speed. We demonstrate the numerical performance of the PIKL estimator through simulations, both in the context of hybrid modeling and in solving PDEs. In particular, we show that PIKL can outperform physics-informed neural networks in terms of both accuracy and computation time. Additionally, we identify cases where PIKL surpasses traditional PDE solvers, particularly in scenarios with noisy boundary conditions.

Retrieval-augmented generation (RAG) improves Large Language Models (LLMs) by incorporating external information into the response generation process. However, how context-faithful LLMs are and what factors influence LLMs' context-faithfulness remain largely unexplored. In this study, we investigate the impact of memory strength and evidence presentation on LLMs' receptiveness to external evidence. We introduce a method to quantify the memory strength of LLMs by measuring the divergence in LLMs' responses to different paraphrases of the same question, which is not considered by previous works. We also generate evidence in various styles to evaluate the effects of evidence in different styles. Two datasets are used for evaluation: Natural Questions (NQ) with popular questions and popQA featuring long-tail questions. Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory, particularly for larger LLMs such as GPT-4. On the other hand, presenting paraphrased evidence significantly increases LLMs' receptiveness compared to simple repetition or adding details.

Background: Test flakiness is a major problem in the software industry. Flaky tests fail seemingly at random without changes to the code and thus impede continuous integration (CI). Some researchers argue that all tests can be considered flaky and that tests only differ in their frequency of flaky failures. Aims: With the goal of developing mitigation strategies to reduce the negative impact of test flakiness, we study characteristics of tests and the test environment that potentially impact test flakiness. Method: We construct two datasets based on SAP HANA's test results over a 12-week period: one based on production data, the other based on targeted test executions from a dedicated flakiness experiment. We conduct correlation analysis for test and test environment characteristics with respect to their influence on the frequency of flaky test failures. Results: In our study, the average test execution time had the strongest positive correlation with the test flakiness rate (r = 0.79), which confirms previous studies. Potential reasons for higher flakiness include the larger test scope of long-running tests or test executions on a slower test infrastructure. Interestingly, the load on the testing infrastructure was not correlated with test flakiness. The relationship between test flakiness and required resources for test execution is inconclusive. Conclusions: Based on our findings, we conclude that splitting long-running tests can be an important measure for practitioners to cope with test flakiness, as it enables parallelization of test executions and also reduces the cost of re-executions. This effectively decreases the negative effects of test flakiness in complex testing environments. However, when splitting long-running tests, practitioners need to consider the potential test setup overhead of test splits., Comment: 10 pages, 8 figures, 4 tables, Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM IGC 2024)

Nonreciprocal thermal emitters that break Kirchhoff's law of thermal radiation promise exciting applications for thermal and energy applications. The design of the bandwidth and angular range of the nonreciprocal effect, which directly affects the performance of nonreciprocal emitters, typically relies on physical intuition. In this study, we present a general numerical approach to maximize the nonreciprocal effect. We choose doped magneto-optic materials and magnetic Weyl semimetal materials as model materials and focus on pattern-free multilayer structures. The optimization randomly starts from a less effective structure and incrementally improves the broadband nonreciprocity through the combination of Bayesian optimization and reparameterization. Optimization results show that the proposed approach can discover structures that can achieve broadband nonreciprocal emission at wavelengths from 5 to 40 micrometers using only a fewer layers, significantly outperforming current state-of-the-art designs based on intuition in terms of both performance and simplicity.

Context. (4015) Wilson-Harrington (hereafter, WH) was discovered as a comet in 1949 but has a dynamical property consistent with that of a near-Earth asteroid. Although there is a report that the 1949 activity is associated with an ion tail, the cause of the activity has not yet been identified. Aims. This work aims to reveal the mysterious comet-like activity of the near-Earth asteroid. Methods. We conducted new polarimetric observations of WH from May 2022 to January 2023, reanalyses of the photographic plate images taken at the time of its discovery in 1949, and dust tail simulation modelings, where the dust terminal velocity and ejection epoch are taken into account. Results. We found that this object shows polarization characteristics similar to those of low-albedo asteroids. We derived the geometric albedo ranging from pV = 0.076 +- 0.010 to pV = 0.094 +- 0.018 from our polarimetry (the values vary depending on the data used for fitting and the slope-albedo relationship coefficients). In addition, the 1949 image showed an increase in brightness around the nucleus. Furthermore, we found that the color of the tail is consistent with sunlight, suggesting that the 1949 activity is associated with dust ejection. From the dust tail analysis, ~9 x 10^5 kg of material was ejected episodically at a low velocity equivalent to or even slower than the escape velocity. Conclusions. We conclude that WH is most likely an active asteroid of main belt origin and that the activity in 1949 was likely triggered by mass shedding due to fast rotation., Comment: 12 pages, 7 figures (Accepted for the publication of Astronomy and Astrophysics)

This paper introduces constraint-based breakpoints, a technique for designing responsive visualizations for a wide variety of screen sizes and datasets. Breakpoints in responsive visualization define when different visualization designs are shown. Conventionally, breakpoints are static, pre-defined widths, and as such do not account for changes to the visualized dataset or visualization parameters. To guarantee readability and efficient use of space across datasets, these static breakpoints would require manual updates. Constraint-based breakpoints solve this by evaluating visualization-specific constraints on the size of visual elements, overlapping elements, and the aspect ratio of the visualization and available space. Once configured, a responsive visualization with constraint-based breakpoints can adapt to different screen sizes for any dataset. We describe a framework that guides designers in creating a stack of visualization designs for different display sizes and defining constraints for each of these designs. We demonstrate constraint-based breakpoints for different data types and their visualizations: geographic data (choropleth map, proportional circle map, Dorling cartogram, hexagonal grid map, bar chart, waffle chart), network data (node-link diagram, adjacency matrix, arc diagram), and multivariate data (scatterplot, heatmap). Interactive demos and supplemental material are available at https://responsive-vis.github.io/breakpoints/., Comment: 12 pages, 9 figures. Accepted to IEEE Transactions on Visualization and Computer Graphics

Diffusion Magnetic Resonance Imaging (dMRI) is a non-invasive method for depicting brain microstructure in vivo. Fiber orientation distributions (FODs) are mathematical representations extensively used to map white matter fiber configurations. Recently, FOD estimation with deep neural networks has seen growing success, in particular, those of neonates estimated with fewer diffusion measurements. These methods are mostly trained on target FODs reconstructed with multi-shell multi-tissue constrained spherical deconvolution (MSMT-CSD), which might not be the ideal ground truth for developing brains. Here, we investigate this hypothesis by training a state-of-the-art model based on the U-Net architecture on both MSMT-CSD and single-shell three-tissue constrained spherical deconvolution (SS3T-CSD). Our results suggest that SS3T-CSD might be more suited for neonatal brains, given that the ratio between single and multiple fiber-estimated voxels with SS3T-CSD is more realistic compared to MSMT-CSD. Additionally, increasing the number of input gradient directions significantly improves performance with SS3T-CSD over MSMT-CSD. Finally, in an age domain-shift setting, SS3T-CSD maintains robust performance across age groups, indicating its potential for more accurate neonatal brain imaging., Comment: 11 pages, 4 figures; accepted as an Oral Presentation at the MICCAI 2024 Workshop on Computational Diffusion MRI (CDMRI) in Marrakech, Morocco

The "Annual Report on People with Disabilities in America" is a companion volume to the "2024 Annual Disability Statistics Compendium." Indicators were in the following areas of interest: employment, educational attainment, health and health care, financial status and security, leisure recreation, personal relationships, and crime/safety.

The "Annual Disability Statistics Compendium," is a summary of statistics about people with disabilities and about the government programs which serve them. The Compendium, presents key overall statistics on topics including the prevalence of disability, employment among persons with disabilities, rates of participation in disability income and social insurance programs, and other statistics. It is a compilation of data from multiple sources, such as the Social Security Administration, Veterans Benefits Administration, and frequently, the U.S. Census Bureau's American Community Survey, among others. A companion "Annual Report" is available, providing graphic representations of key findings.

Purpose: To develop an open-source nnU-Net-based AI model for combined detection and segmentation of unruptured intracranial aneurysms (UICA) in 3D TOF-MRI, and compare models trained on datasets with aneurysm-like differential diagnoses. Methods: This retrospective study (2020-2023) included 385 anonymized 3D TOF-MRI images from 364 patients (mean age 59 years, 60% female) at multiple centers plus 113 subjects from the ADAM challenge. Images featured untreated or possible UICAs and differential diagnoses. Four distinct training datasets were created, and the nnU-Net framework was used for model development. Performance was assessed on a separate test set using sensitivity and False Positive (FP)/case rate for detection, and DICE score and NSD (Normalized Surface Distance) with a 0.5mm threshold for segmentation. Statistical analysis included chi-square, Mann-Whitney-U, and Kruskal-Wallis tests, with significance set at p < 0.05. Results: Models achieved overall sensitivity between 82% and 85% and a FP/case rate of 0.20 to 0.31, with no significant differences (p = 0.90 and p = 0.16). The primary model showed 85% sensitivity and 0.23 FP/case rate, outperforming the ADAM-challenge winner (61%) and a nnU-Net trained on ADAM data (51%) in sensitivity (p < 0.05). It achieved a mean DICE score of 0.73 and an NSD of 0.84 for correctly detected UICA. Conclusions: Our open-source, nnU-Net-based AI model (available at 10.5281/zenodo.13386859) demonstrates high sensitivity, low false positive rates, and consistent segmentation accuracy for UICA detection and segmentation in 3D TOF-MRI, suggesting its potential to improve clinical diagnosis and for monitoring of UICA., Comment: 14 pages, 5 figures, 3 tables, 2 supplementary tables

In this paper, we study the statistical and geometrical properties of the Kullback-Leibler divergence with kernel covariance operators (KKL) introduced by Bach [2022]. Unlike the classical Kullback-Leibler (KL) divergence that involves density ratios, the KKL compares probability distributions through covariance operators (embeddings) in a reproducible kernel Hilbert space (RKHS), and compute the Kullback-Leibler quantum divergence. This novel divergence hence shares parallel but different aspects with both the standard Kullback-Leibler between probability distributions and kernel embeddings metrics such as the maximum mean discrepancy. A limitation faced with the original KKL divergence is its inability to be defined for distributions with disjoint supports. To solve this problem, we propose in this paper a regularised variant that guarantees that the divergence is well defined for all distributions. We derive bounds that quantify the deviation of the regularised KKL to the original one, as well as finite-sample bounds. In addition, we provide a closed-form expression for the regularised KKL, specifically applicable when the distributions consist of finite sets of points, which makes it implementable. Furthermore, we derive a Wasserstein gradient descent scheme of the KKL divergence in the case of discrete distributions, and study empirically its properties to transport a set of points to a target distribution.

Concentration inequalities, a major tool in probability theory, quantify how much a random variable deviates from a certain quantity. This paper proposes a systematic convex optimization approach to studying and generating concentration inequalities with independent random variables. Specifically, we extend the generalized problem of moments to independent random variables. We first introduce a variational approach that extends classical moment-generating functions, focusing particularly on first-order moment conditions. Second, we develop a polynomial approach, based on a hierarchy of sum-of-square approximations, to extend these techniques to higher-moment conditions. Building on these advancements, we refine Hoeffding's, Bennett's and Bernstein's inequalities, providing improved worst-case guarantees compared to existing results.

In the present noisy intermediate scale quantum computing era, there is a critical need to devise methods for the efficient implementation of gate-based variational quantum circuits. This ensures that a range of proposed applications can be deployed on real quantum hardware. The efficiency of quantum circuit is desired both in the number of trainable gates and the depth of the overall circuit. The major concern of barren plateaus has made this need for efficiency even more acute. The problem of efficient quantum circuit realization has been extensively studied in the literature to reduce gate complexity and circuit depth. Another important approach is to design a method to reduce the \emph{parameter complexity} in a variational quantum circuit. Existing methods include hyperparameter-based parameter pruning which introduces an additional challenge of finding the best hyperparameters for different applications. In this paper, we present \emph{QAdaPrune} - an adaptive parameter pruning algorithm that automatically determines the threshold and then intelligently prunes the redundant and non-performing parameters. We show that the resulting sparse parameter sets yield quantum circuits that perform comparably to the unpruned quantum circuits and in some cases may enhance trainability of the circuits even if the original quantum circuit gets stuck in a barren plateau.\\ \noindent{\bf Reproducibility}: The source code and data are available at \url{https://github.com/aicaffeinelife/QAdaPrune.git}

Performance testing in large-scale database systems like SAP HANA is a crucial yet labor-intensive task, involving extensive manual analysis of thousands of measurements, such as CPU time and elapsed time. Manual maintenance of these metrics is time-consuming and susceptible to human error, making early detection of performance regressions challenging. We address these issues by proposing an automated approach to detect performance regressions in such measurements. Our approach integrates Bayesian inference with the Pruned Exact Linear Time (PELT) algorithm, enhancing the detection of change points and performance regressions with high precision and efficiency compared to previous approaches. Our method minimizes false negatives and ensures SAP HANA's system's reliability and performance quality. The proposed solution can accelerate testing and contribute to more sustainable performance management practices in large-scale data management environments.

To date, several methods have been developed to explain deep learning algorithms for classification tasks. Recently, an adaptation of two of such methods has been proposed to generate instance-level explainable maps in a semantic segmentation scenario, such as multiple sclerosis (MS) lesion segmentation. In the mentioned work, a 3D U-Net was trained and tested for MS lesion segmentation, yielding an F1 score of 0.7006, and a positive predictive value (PPV) of 0.6265. The distribution of values in explainable maps exposed some differences between maps of true and false positive (TP/FP) examples. Inspired by those results, we explore in this paper the use of characteristics of lesion-specific saliency maps to refine segmentation and detection scores. We generate around 21000 maps from as many TP/FP lesions in a batch of 72 patients (training set) and 4868 from the 37 patients in the test set. 93 radiomic features extracted from the first set of maps were used to train a logistic regression model and classify TP versus FP. On the test set, F1 score and PPV were improved by a large margin when compared to the initial model, reaching 0.7450 and 0.7817, with 95% confidence intervals of [0.7358, 0.7547] and [0.7679, 0.7962], respectively. These results suggest that saliency maps can be used to refine prediction scores, boosting a model's performances.

Quantum approximate optimization is one of the promising candidates for useful quantum computation, particularly in the context of finding approximate solutions to Quadratic Unconstrained Binary Optimization (QUBO) problems. However, the existing quantum processing units (QPUs) are relatively small, and canonical mappings of QUBO via the Ising model require one qubit per variable, rendering direct large-scale optimization infeasible. In classical optimization, a general strategy for addressing many large-scale problems is via multilevel/multigrid methods, where the large target problem is iteratively coarsened, and the global solution is constructed from multiple small-scale optimization runs. In this work, we experimentally test how existing QPUs perform as a sub-solver within such a multilevel strategy. We combine and extend (via additional classical processing) the recent Noise-Directed Adaptive Remapping (NDAR) and Quantum Relax $\&$ Round (QRR) algorithms. We first demonstrate the effectiveness of our heuristic extensions on Rigetti's transmon device Ankaa-2. We find approximate solutions to $10$ instances of fully connected $82$-qubit Sherrington-Kirkpatrick graphs with random integer-valued coefficients obtaining normalized approximation ratios (ARs) in the range $\sim 0.98-1.0$, and the same class with real-valued coefficients (ARs $\sim 0.94-1.0$). Then, we implement the extended NDAR and QRR algorithms as subsolvers in the multilevel algorithm for $6$ large-scale graphs with at most $\sim 27,000$ variables. The QPU (with classical post-processing steps) is used to find approximate solutions to dozens of problems, at most $82$-qubit, which are iteratively used to construct the global solution. We observe that quantum optimization results are competitive regarding the quality of solutions compared to classical heuristics used as subsolvers within the multilevel approach., Comment: 7+3 pages; 6+0 figures; 2+0 tables; comments and suggestions are welcome!

This paper defines, analyzes, and discusses the emerging genre of visualization atlases. We currently witness an increase in web-based, data-driven initiatives that call themselves "atlases" while explaining complex, contemporary issues through data and visualizations: climate change, sustainability, AI, or cultural discoveries. To understand this emerging genre and inform their design, study, and authoring support, we conducted a systematic analysis of 33 visualization atlases and semi-structured interviews with eight visualization atlas creators. Based on our results, we contribute (1) a definition of a visualization atlas as a compendium of (web) pages aimed at explaining and supporting exploration of data about a dedicated topic through data, visualizations and narration. (2) a set of design patterns of 8 design dimensions, (3) insights into the atlas creation from interviews and (4) the definition of 5 visualization atlas genres. We found that visualization atlases are unique in the way they combine i) exploratory visualization, ii) narrative elements from data-driven storytelling and iii) structured navigation mechanisms. They target a wide range of audiences with different levels of domain knowledge, acting as tools for study, communication, and discovery. We conclude with a discussion of current design practices and emerging questions around the ethics and potential real-world impact of visualization atlases, aimed to inform the design and study of visualization atlases.

People often face trade-offs between costs and benefits occurring at various points in time. The predominant discounting approach is to use the exponential form. Central to this approach is the discount rate, a unique parameter that converts a future value into its present equivalent. However, a universally accepted discount rate remains a matter of ongoing debate and lacks consensus. This paper provides a robust solution for resolving conflicts in discount rates, which recommends considering all discount rates but aims to assign varying degrees of importance to these rates. Moreover, a considerable number of economists support a theory that suggests equal consideration of future and present utilities. In response to this debate, we introduce a general criterion capable of accommodating situations where it is feasible not to discount future utilities. This criterion encompasses and extends various existing criteria in the literature.

We investigate bilayers of nanoporous graphene (NPG), laterally bonded carbon nanoribbons, and graphene. The electronic and transport properties are explored as a function of the interlayer twist angle using an atomistic tight-binding model combined with non-equilibrium Green's functions. At small twist angles ($\theta \lesssim 10^\circ$), NPG and graphene are strongly coupled, as revealed by the hybridization of their electronic bands. As a result, when electrons are point-injected in NPG, a substantial interlayer transmission occurs and an electronic Talbot-like interference pattern appears in the current flow on both layers. Besides, the twist-induced mirror-symmetry-breaking leads to chiral features in the injected current. Upon increasing the twist angle, the coupling is weakened and the monolayer electronic properties are restored. Furthermore, we demonstrate the emergence of resonant peaks in the electronic density of states for small twist angles, allowing to probe the twist-dependent interlayer coupling via scanning tunneling microscopy., Comment: 6+7 pages, 4+6 figures

This paper presents an interactive technique to explain visual patterns in network visualizations to analysts who do not understand these visualizations and who are learning to read them. Learning a visualization requires mastering its visual grammar and decoding information presented through visual marks, graphical encodings, and spatial configurations. To help people learn network visualization designs and extract meaningful information, we introduce the concept of interactive pattern explanation that allows viewers to select an arbitrary area in a visualization, then automatically mines the underlying data patterns, and explains both visual and data patterns present in the viewer's selection. In a qualitative and a quantitative user study with a total of 32 participants, we compare interactive pattern explanations to textual-only and visual-only (cheatsheets) explanations. Our results show that interactive explanations increase learning of i) unfamiliar visualizations, ii) patterns in network science, and iii) the respective network terminology., Comment: to be published in IEEE VIS 2024

The problem of adopting quantum-resistant cryptographic network protocols or post-quantum cryptography (PQC) is critically important to democratizing quantum computing. The problem is urgent because practical quantum computers will break classical encryption in the next few decades. Past encrypted data has already been collected and can be decrypted in the near future. The main challenges of adopting post-quantum cryptography lie in algorithmic complexity and hardware/software/network implementation. The grand question of how existing cyberinfrastructure will support post-quantum cryptography remains unanswered. This paper describes: i) the design of a novel Post-Quantum Cryptography (PQC) network instrument placed at the National Center for Supercomputing Applications (NCSA) at the University of Illinois at Urbana-Champaign and a part of the FABRIC testbed; ii) the latest results on PQC adoption rate across a wide spectrum of network protocols (Secure Shell -- SSH, Transport Layer Security -- TLS, etc.); iii) the current state of PQC implementation in key scientific applications (e.g., OpenSSH or SciTokens); iv) the challenges of being quantum-resistant; and v) discussion of potential novel attacks. This is the first large-scale measurement of PQC adoption at national-scale supercomputing centers and FABRIC testbeds. Our results show that only OpenSSH and Google Chrome have successfully implemented PQC and achieved an initial adoption rate of 0.029% (6,044 out of 20,556,816) for OpenSSH connections at NCSA coming from major Internet Service Providers or Autonomous Systems (ASes) such as OARNET, GTT, Google Fiber Webpass (U.S.) and Uppsala Lans Landsting (Sweden), with an overall increasing adoption rate year-over-year for 2023-2024. Our analyses identify pathways to migrate current applications to be quantum-resistant., Comment: Accepted at IEEE QCE 2024