Search

The Maxwell's equations, a system of linear partial differential equations (PDEs), describe the behavior of electric and magnetic fields in time and space and is essential for many important electromagnetic applications. Although numerical methods have been applied successfully in the past, the primary challenge in solving these equations arises from the frequency of electromagnetic fields, which depends on the shape and size of the objects to be resolved. The frequency dictates the grid size used for the spatial discretization of the PDEs. Since the domain of influence for these equations is compactly supported, even a small perturbation in frequency necessitates a new discretization of Maxwell's equations, resulting in substantial computational costs. In this work, we investigate the potential of neural operators, particularly the Deep Operator Network (DeepONet) and its variants, as a surrogate model for Maxwell's equations. Existing DeepONet implementations are restricted to real-valued data in $\mathbb{R}^n$, but since the time-harmonic Maxwell's equations yield solutions in the complex domain $\mathbb{C}^n$, a specialized architecture is required to handle complex algebra. We propose a formulation of DeepONet for complex data, define the forward pass in the complex domain, and adopt a reparametrized version of DeepONet for more efficient training. We also propose a unified framework to combine a plurality of DeepONets, trained for multiple electromagnetic field components, to incorporate the boundary condition. As shown by computational experiments, our method significantly enhances the efficiency of predicting scattered fields from a spherical object at arbitrary high frequencies.

Osteoporosis, a prevalent condition among the aging population worldwide, is characterized by diminished bone mass and altered bone structure, increasing susceptibility to fractures. It poses a significant and growing global public health challenge over the next decade. Diagnosis typically involves Dual-energy X-ray absorptiometry to measure bone mineral density, yet its mass screening utility is limited. The Singh Index (SI) provides a straightforward, semi-quantitative means of osteoporosis diagnosis through plain hip radiographs, assessing trabecular patterns in the proximal femur. Although cost-effective and accessible, manual SI calculation is time-intensive and requires expertise. This study aims to automate SI identification from radiographs using machine learning algorithms. An unlabelled dataset of 838 hip X-ray images from Indian adults aged 20-70 was utilized. A custom convolutional neural network architecture was developed for feature extraction, demonstrating superior performance in cluster homogeneity and heterogeneity compared to established models. Various clustering algorithms categorized images into six SI grade clusters, with comparative analysis revealing only two clusters with high Silhouette Scores for promising classification. Further scrutiny highlighted dataset imbalance and emphasized the importance of image quality and additional clinical data availability. The study suggests augmenting X-ray images with patient clinical data and reference images, alongside image pre-processing techniques, to enhance diagnostic accuracy. Additionally, exploring semi-supervised and self-supervised learning methods may mitigate labelling challenges associated with large datasets.

We present results for the distance sensitivity oracle (DSO) problem, where one needs to preprocess a given directed weighted graph $G=(V,E)$ in order to answer queries about the shortest path distance from $s$ to $t$ in $G$ that avoids edge $e$, for any $s,t \in V, e \in E$. No non-trivial results are known for DSO in the distributed CONGEST model even though it is of importance to maintain efficient communication under an edge failure. Let $n=|V|$, and let $D$ be the undirected diameter of $G$. Our first DSO algorithm optimizes query response rounds and can answer a batch of any $k\geq 1$ queries in $O(k+D)$ rounds after taking $\tilde{O}(n^{3/2})$ rounds to preprocess $G$. Our second algorithm takes $\tilde{O}(n)$ rounds for preprocessing, and then it can answer any batch of $k\geq 1$ queries in $\tilde{O}(k\sqrt{n}+D)$ rounds. We complement these algorithms with some unconditional CONGEST lower bounds that give trade-offs between preprocessing rounds and rounds needed to answer queries. Additionally, we present almost-optimal upper and lower bounds for the related all pairs second simple shortest path (2-APSiSP) problem, where for all pairs of vertices $x,y \in V$, we need to compute the minimum weight of a simple $x$-$y$ path that differs from the precomputed $x$-$y$ shortest path by at least one edge.

Active learning (AL) is for optimizing the selection of unlabeled data for annotation (labeling), aiming to enhance model performance while minimizing labeling effort. The key question in AL is which unlabeled data should be selected for annotation. Existing deep AL methods arguably suffer from bias incurred by clabeled data, which takes a much lower percentage than unlabeled data in AL context. We observe that such an issue is severe in different types of data, such as vision and non-vision data. To address this issue, we propose a novel method, namely Manifold-Preserving Trajectory Sampling (MPTS), aiming to enforce the feature space learned from labeled data to represent a more accurate manifold. By doing so, we expect to effectively correct the bias incurred by labeled data, which can cause a biased selection of unlabeled data. Despite its focus on manifold, the proposed method can be conveniently implemented by performing distribution mapping with MMD (Maximum Mean Discrepancies). Extensive experiments on various vision and non-vision benchmark datasets demonstrate the superiority of our method. Our source code can be found here.

This project proposes the development of a comprehensive real-time biodiversity monitoring system that harnesses sound data through a network of acoustic sensors and advanced artificial intelligence algorithms. The system analyzes sound recordings from various ecosystems to identify and classify different species, providing valuable insights into ecosystem health and biodiversity patterns while facilitating the detection of subtle changes in species presence and behavior over time. By addressing critical challenges such as noise pollution and species overlap, the system employs sophisticated filtering and classification techniques to ensure accurate and reliable monitoring, distinguishing between natural sounds and anthropogenic noise. Ultimately, this initiative aims to enhance our understanding of biodiversity dynamics and provide essential information to support effective conservation strategies and inform policy decisions, empowering stakeholders with actionable insights to protect and preserve vital ecosystems.

The cellular wireless networks are evolving towards acquiring newer capabilities, such as sensing, which will support novel use cases and applications. Many of these require indoor sensing capabilities, which can be realized by exploiting the perturbation in the indoor channel. In this work, we conduct an indoor channel measurement campaign to study these perturbations and develop AI-based algorithms for estimating sensing parameters. We develop several AI methods based on CNN and tree-based ensemble architectures for sensing. We show that the presence of a passive target like a person can be detected from the channel perturbation of a single link with more than 90 % accuracy with a simple CNN based AI algorithm. However, sensing the position of a passive target is far more challenging requiring more complex AI algorithms and deployments. We show that the position of the human in the indoor room can be estimated within the average position error of 0.7 m with a deployment having three links and employing complex AI architecture for position estimation. We also compare the results with the baseline algorithm to demonstrate the utility of the proposed method., Comment: 4 Pages of technical content and 5th page with reference. Submitted to ICASSP 2025

Underwater imagery is often compromised by factors such as color distortion and low contrast, posing challenges for high-level vision tasks. Recent underwater image restoration (UIR) methods either analyze the input image at full resolution, resulting in spatial richness but contextual weakness, or progressively from high to low resolution, yielding reliable semantic information but reduced spatial accuracy. Here, we propose a lightweight multi-stage network called Lit-Net that focuses on multi-resolution and multi-scale image analysis for restoring underwater images while retaining original resolution during the first stage, refining features in the second, and focusing on reconstruction in the final stage. Our novel encoder block utilizes parallel $1\times1$ convolution layers to capture local information and speed up operations. Further, we incorporate a modified weighted color channel-specific $l_1$ loss ($cl_1$) function to recover color and detail information. Extensive experimentations on publicly available datasets suggest our model's superiority over recent state-of-the-art methods, with significant improvement in qualitative and quantitative measures, such as $29.477$ dB PSNR ($1.92\%$ improvement) and $0.851$ SSIM ($2.87\%$ improvement) on the EUVP dataset. The contributions of Lit-Net offer a more robust approach to underwater image enhancement and super-resolution, which is of considerable importance for underwater autonomous vehicles and surveillance. The code is available at: https://github.com/Alik033/Lit-Net.

Modern model serving engines infer prompts on large language models in batches. While batch processing prompts leads to high inference throughput, it delays responding to requests that do not fit in a batch, potentially starving them. We propose that fair scheduling prompts for inference by time-sharing GPUs cycles, instead of batch processing them, is key to preventing prompt starvation and achieving responsive inference. However, time-shared prompt scheduling incurs the overhead of frequently paging dynamic context needed to infer a prompt back into GPU memory. Today, serving engines support paging inference context between GPU memory and the host DRAM. The overhead of transferring context from DRAM to GPU memory is high since it is lower-bounded by the limited PCIe bandwidth. We overcome this challenge by offloading inference context from a GPU to the memory of another GPU on the same server, connected via inter-GPU interconnects that support magnitudes higher bandwidth than PCIe. We achieve this by developing AQUA, a transparent and elastic GPU memory management framework for responsive LLM inference. We evaluate AQUA by hosting eight state-of-the-art large generative ML models of different modalities (e.g., text, audio, vision) on a server with 8 cutting-edge Nvidia A100 80G GPUs. Using representative inference workloads, we show that AQUA improves the responsiveness of LLM inference by 4X compared to the state-of-the-art and it improves LLM inference throughput over a single long prompt by 6X.

We find the commutant of a pure contractive semigroup on a Hilbert space. We demonstrate that any tuple of doubly commuting pure contractive semigroups can be dilated to a tuple of doubly commuting pure isometric semigroups. En route, we obtain a complete model for the tuples of doubly commuting isometric semigroups., Comment: Preliminary version, comments are welcome

Aditya-L1 is the first Indian solar mission placed at the first Lagrangian (L1) point to study the Sun. A fluxgate magnetometer (MAG) is one of the seven payloads and one of the three in-situ payloads onboard to measure the interplanetary magnetic field (IMF) coming from the Sun towards the Earth. At present, the Aditya-L1 spacecraft is in a halo-orbit around the L1 point and the MAG payload is ON is continuously measuring the IMF. This paper presents the first measurements of the IMF by MAG.

Argument Mining (AM) involves identifying and extracting Argumentative Components (ACs) and their corresponding Argumentative Relations (ARs). Most of the prior works have broken down these tasks into multiple sub-tasks. Existing end-to-end setups primarily use the dependency parsing approach. This work introduces a generative paradigm-based end-to-end framework argTANL. argTANL frames the argumentative structures into label-augmented text, called Augmented Natural Language (ANL). This framework jointly extracts both ACs and ARs from a given argumentative text. Additionally, this study explores the impact of Argumentative and Discourse markers on enhancing the model's performance within the proposed framework. Two distinct frameworks, Marker-Enhanced argTANL (ME-argTANL) and argTANL with specialized Marker-Based Fine-Tuning, are proposed to achieve this. Extensive experiments are conducted on three standard AM benchmarks to demonstrate the superior performance of the ME-argTANL.

Probabilistic forecasting models for joint distributions of targets in irregular time series are a heavily under-researched area in machine learning with, to the best of our knowledge, only three models researched so far: GPR, the Gaussian Process Regression model~\citep{Durichen2015.Multitask}, TACTiS, the Transformer-Attentional Copulas for Time Series~\cite{Drouin2022.Tactis, ashok2024tactis} and ProFITi \citep{Yalavarthi2024.Probabilistica}, a multivariate normalizing flow model based on invertible attention layers. While ProFITi, thanks to using multivariate normalizing flows, is the more expressive model with better predictive performance, we will show that it suffers from marginalization inconsistency: it does not guarantee that the marginal distributions of a subset of variables in its predictive distributions coincide with the directly predicted distributions of these variables. Also, TACTiS does not provide any guarantees for marginalization consistency. We develop a novel probabilistic irregular time series forecasting model, Marginalization Consistent Mixtures of Separable Flows (moses), that mixes several normalizing flows with (i) Gaussian Processes with full covariance matrix as source distributions and (ii) a separable invertible transformation, aiming to combine the expressivity of normalizing flows with the marginalization consistency of Gaussians. In experiments on four different datasets we show that moses outperforms other state-of-the-art marginalization consistent models, performs on par with ProFITi, but different from ProFITi, guarantee marginalization consistency.

We consider holomorphic functions on the unit disc whose images are contained in a strip of the complex plane. Under an additional condition, such functions are constants. We also consider appropriate operator valued versions. Applications are found to the theory of semigroups., Comment: To appear in Infinite Dimensional Analysis, Quantum Probability and Related Topics

Irregularly sampled time series with missing values are often observed in multiple real-world applications such as healthcare, climate and astronomy. They pose a significant challenge to standard deep learning models that operate only on fully observed and regularly sampled time series. In order to capture the continuous dynamics of the irregular time series, many models rely on solving an Ordinary Differential Equation (ODE) in the hidden state. These ODE-based models tend to perform slow and require large memory due to sequential operations and a complex ODE solver. As an alternative to complex ODE-based models, we propose a family of models called Functional Latent Dynamics (FLD). Instead of solving the ODE, we use simple curves which exist at all time points to specify the continuous latent state in the model. The coefficients of these curves are learned only from the observed values in the time series ignoring the missing values. Through extensive experiments, we demonstrate that FLD achieves better performance compared to the best ODE-based model while reducing the runtime and memory overhead. Specifically, FLD requires an order of magnitude less time to infer the forecasts compared to the best performing forecasting model.

The use of automotive radars is gaining popularity as a means to enhance a vehicle's sensing capabilities. However, these radars can suffer from interference caused by transmissions from other radars mounted on nearby vehicles. To address this issue, we investigate the use of an onboard intelligent reflective surface (IRS) to artificially increase a vehicle's effective radar cross section (RCS), or its "electromagnetic visibility." Our proposed method utilizes the IRS's ability to form a coherent reflection of the incident radar waveform back towards the source radar, thereby improving radar performance under interference. We evaluated both passive and active IRS options. Passive IRS, which does not support reflection amplification, was found to be counter-productive and actually decreased the vehicle's effective RCS instead of enhancing it. In contrast, active IRS, which can amplify the reflection power of individual elements, effectively combats all types of automotive radar interference when the reflective elements are configured with a 15-35 dB reflection gain., Comment: 7 pages, 9 Figures

As with most other data domains, EEG data analysis relies on rich domain-specific preprocessing. Beyond such preprocessing, machine learners would hope to deal with such data as with any other time series data. For EEG classification many models have been developed with layer types and architectures we typically do not see in time series classification. Furthermore, typically separate models for each individual subject are learned, not one model for all of them. In this paper, we systematically study the differences between EEG classification models and generic time series classification models. We describe three different model setups to deal with EEG data from different subjects, subject-specific models (most EEG literature), subject-agnostic models and subject-conditional models. In experiments on three datasets, we demonstrate that off-the-shelf time series classification models trained per subject perform close to EEG classification models, but that do not quite reach the performance of domain-specific modeling. Additionally, we combine time-series models with subject embeddings to train one joint subject-conditional classifier on all subjects. The resulting models are competitive with dedicated EEG models in 2 out of 3 datasets, even outperforming all EEG methods on one of them.

Spectral clustering methods have gained widespread recognition for their effectiveness in clustering high-dimensional data. Among these techniques, constrained spectral clustering has emerged as a prominent approach, demonstrating enhanced performance by integrating pairwise constraints. However, the application of such constraints to semidefinite spectral clustering, a variant that leverages semidefinite programming to optimize clustering objectives, remains largely unexplored. In this paper, we introduce a novel framework for seamlessly integrating pairwise constraints into semidefinite spectral clustering. Our methodology systematically extends the capabilities of semidefinite spectral clustering to capture complex data structures, thereby addressing real-world clustering challenges more effectively. Additionally, we extend this framework to encompass both active and self-taught learning scenarios, further enhancing its versatility and applicability. Empirical studies conducted on well-known datasets demonstrate the superiority of our proposed framework over existing spectral clustering methods, showcasing its robustness and scalability across diverse datasets and learning settings. By bridging the gap between constrained learning and semidefinite spectral clustering, our work contributes to the advancement of spectral clustering techniques, offering researchers and practitioners a versatile tool for addressing complex clustering challenges in various real-world applications. Access to the data, code, and experimental results is provided for further exploration (https://github.com/swarupbehera/SCCCS).