Search

Empirical software engineering faces a critical gap: the lack of standardized tools for rapid development and execution of Test-Driven Software Experiments (TDSEs) - that is, experiments that involve the execution of software subjects and the observation and analysis of their "de facto" run-time behavior. In this paper we present a general-purpose analysis platform called LASSO that provides a minimal set of domain-specific languages and data structures to conduct TDSEs. By empowering users with an executable scripting language to design and execute TDSEs, LASSO enables efficient evaluation of run-time semantics and execution characteristics in addition to statically determined properties. We present an example TDSE that demonstrates the practical benefits of LASSO's scripting capabilities for assessing the reliability of LLMs for code generation by means of a self-contained, reusable and extensible study script. The LASSO platform is freely available at: https://softwareobservatorium.github.io/, and a demo video is available on YouTube: https://youtu.be/tzY9oNTWXzw

Generative AI (GAI) holds great potential to improve software engineering productivity, but its untrustworthy outputs, particularly in code synthesis, pose significant challenges. The need for extensive verification and validation (V&V) of GAI-generated artifacts may undermine the potential productivity gains. This paper proposes a way of mitigating these risks by exploiting GAI's ability to generate multiple versions of code and tests to facilitate comparative analysis across versions. Rather than relying on the quality of a single test or code module, this "differential GAI" (D-GAI) approach promotes more reliable quality evaluation through version diversity. We introduce the Large-Scale Software Observatorium (LASSO), a platform that supports D-GAI by executing and analyzing large sets of code versions and tests. We discuss how LASSO enables rigorous evaluation of GAI-generated artifacts and propose its application in both software development and GAI research., Comment: This work has been accepted for publication in an upcoming issue of IEEE Software. This work has been submitted to the IEEE for possible publication

This is a paper in the field of ontological deterministic theories behind Quantum Field Theories, like for example the cellular automaton theories proposed by 't Hooft. In these theories one has ontological states in which the state of reality is exactly known and no uncertainties are present. Also these states evolve in time deterministically. A first step in finding the ontological deterministic theory behind the Standard Model is to find in Quantum Field Theory the states that behave as ontological states. We present the ontological states for all non-interacting (3+1-dimensional) Quantum Field Theories occurring in the Standard Model. We summarize the ontological states for free scalar bosons and for free masless Dirac fermions, which are known from the literature. We construct the ontological states for vector bosons, in analogy to the scalar boson case. With this we have a set of ontological states for all particles that are known to occur in reality and in the Standard Model., Comment: 14 pages

Equivariant neural networks have in recent years become an important technique for guiding architecture selection for neural networks with many applications in domains ranging from medical image analysis to quantum chemistry. In particular, as the most general linear equivariant layers with respect to the regular representation, group convolutions have been highly impactful in numerous applications. Although equivariant architectures have been studied extensively, much less is known about the training dynamics of equivariant neural networks. Concurrently, neural tangent kernels (NTKs) have emerged as a powerful tool to analytically understand the training dynamics of wide neural networks. In this work, we combine these two fields for the first time by giving explicit expressions for NTKs of group convolutional neural networks. In numerical experiments, we demonstrate superior performance for equivariant NTKs over non-equivariant NTKs on a classification task for medical images., Comment: 13 pages + 5 pages appendices

In this paper, we propose a novel and powerful method to harness Bayesian optimization for Variational Quantum Eigensolvers (VQEs) -- a hybrid quantum-classical protocol used to approximate the ground state of a quantum Hamiltonian. Specifically, we derive a VQE-kernel which incorporates important prior information about quantum circuits: the kernel feature map of the VQE-kernel exactly matches the known functional form of the VQE's objective function and thereby significantly reduces the posterior uncertainty. Moreover, we propose a novel acquisition function for Bayesian optimization called Expected Maximum Improvement over Confident Regions (EMICoRe) which can actively exploit the inductive bias of the VQE-kernel by treating regions with low predictive uncertainty as indirectly ``observed''. As a result, observations at as few as three points in the search domain are sufficient to determine the complete objective function along an entire one-dimensional subspace of the optimization landscape. Our numerical experiments demonstrate that our approach improves over state-of-the-art baselines., Comment: 36 pages, 17 figures, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

The ability of Generative AI (GAI) technology to automatically check, synthesize and modify software engineering artifacts promises to revolutionize all aspects of software engineering. Using GAI for software engineering tasks is consequently one of the most rapidly expanding fields of software engineering research, with over a hundred LLM-based code models having been published since 2021. However, the overwhelming majority of existing code models share a major weakness - they are exclusively trained on the syntactic facet of software, significantly lowering their trustworthiness in tasks dependent on software semantics. To address this problem, a new class of "Morescient" GAI is needed that is "aware" of (i.e., trained on) both the semantic and static facets of software. This, in turn, will require a new generation of software observation platforms capable of generating large quantities of execution observations in a structured and readily analyzable way. In this paper, we present a vision and roadmap for how such "Morescient" GAI models can be engineered, evolved and disseminated according to the principles of open science., Comment: To appear in ACM Transactions on Software Engineering and Methodology, Special Issue "2030 Roadmap Software Engineering"

Quantum computing has the potential for disruptive change in many sectors of industry, especially in materials science and optimization. In this paper, we describe how the Turbine Balancing Problem can be solved with quantum computing, which is the NP-hard optimization problem of analytically balancing rotor blades in a single plane as found in turbine assembly. Small yet relevant instances occur in industry, which makes the problem interesting for early quantum computing benchmarks. We model it as a Quadratic Unconstrained Binary Optimization problem and compare the performance of a classical rule-based heuristic and D-Wave Systems' Quantum Annealer Advantage_system4.1. In this case study, we use real-world as well as synthetic datasets and observe that the quantum hardware significantly improves an actively used heuristic's solution for small-scale problem instances with bare disk imbalance in terms of solution quality. Motivated by this performance gain, we subsequently design a quantum-inspired classical heuristic based on simulated annealing that achieves extremely good results on all given problem instances, essentially solving the optimization problem sufficiently well for all considered datasets, according to industrial requirements., Comment: 6 pages, 3 figure

Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training. However, they are often prohibitively more expensive from a computational point of view and cannot be applied to maximum likelihood training in a scalable manner, which severely hinders their widespread adoption. In this work, we overcome these crucial limitations. Specifically, we propose a fast path gradient estimator which improves computational efficiency significantly and works for all normalizing flow architectures of practical relevance. We then show that this estimator can also be applied to maximum likelihood training for which it has a regularizing effect as it can take the form of a given target energy function into account. We empirically establish its superior performance and reduced variance for several natural sciences applications.

We show that deep ensembles become equivariant for all inputs and at all training times by simply using data augmentation. Crucially, equivariance holds off-manifold and for any architecture in the infinite width limit. The equivariance is emergent in the sense that predictions of individual ensemble members are not equivariant but their collective prediction is. Neural tangent kernel theory is used to derive this result and we verify our theoretical insights using detailed numerical experiments., Comment: 11 pages + 17 pages appendices

In silico screening uses predictive models to select a batch of compounds with favorable properties from a library for experimental validation. Unlike conventional learning paradigms, success in this context is measured by the performance of the predictive model on the selected subset of compounds rather than the entire set of predictions. By extending learning theory, we show that the selectivity of the selection policy can significantly impact generalization, with a higher risk of errors occurring when exclusively selecting predicted positives and when targeting rare properties. Our analysis suggests a way to mitigate these challenges. We show that generalization can be markedly enhanced when considering a model's ability to predict the fraction of desired outcomes in a batch. This is promising, as the primary aim of screening is not necessarily to pinpoint the label of each compound individually, but rather to assemble a batch enriched for desirable compounds. Our theoretical insights are empirically validated across diverse tasks, architectures, and screening scenarios, underscoring their applicability., Comment: 9 pages, 3 figures

The increasing importance of carbon capture technologies for deployment in remediating CO2 emissions, and thus the necessity to improve capture materials to allow scalability and efficiency, faces the challenge of materials development, which can require substantial costs and time. Machine learning offers a promising method for reducing the time and resource burdens of materials development through efficient correlation of structure-property relationships to allow down-selection and focusing on promising candidates. Towards demonstrating this, we have developed an end-to-end "discovery cycle" to select new aqueous amines compatible with the commercially viable acid gas scrubbing carbon capture. We combine a simple, rapid laboratory assay for CO2 absorption with a machine learning based molecular fingerprinting model approach. The prediction process shows 60% accuracy against experiment for both material parameters and 80% for a single parameter on an external test set. The discovery cycle determined several promising amines that were verified experimentally, and which had not been applied to carbon capture previously. In the process we have compiled a large, single-source data set for carbon capture amines and produced an open source machine learning tool for the identification of amine molecule candidates (https://github.com/IBM/Carbon-capture-fingerprint-generation)., Comment: 21 single-column pages (LaTex article), 8 figures, 2 tables, separate ESI

We study the consequences of mode-collapse of normalizing flows in the context of lattice field theory. Normalizing flows allow for independent sampling. For this reason, it is hoped that they can avoid the tunneling problem of local-update MCMC algorithms for multi-modal distributions. In this work, we first point out that the tunneling problem is also present for normalizing flows but is shifted from the sampling to the training phase of the algorithm. Specifically, normalizing flows often suffer from mode-collapse for which the training process assigns vanishingly low probability mass to relevant modes of the physical distribution. This may result in a significant bias when the flow is used as a sampler in a Markov-Chain or with Importance Sampling. We propose a metric to quantify the degree of mode-collapse and derive a bound on the resulting bias. Furthermore, we propose various mitigation strategies in particular in the context of estimating thermodynamic observables, such as the free energy., Comment: 10 pages, 7 figures, 6 pages of supplement material

We propose a unifying approach that starts from the perturbative construction of trivializing maps by L\"uscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of lattice field theory and requires several orders of magnitude fewer parameters than any existing machine learning approach. Specifically, our model can achieve competitive performance with as few as 14 parameters while existing deep-learning models have around 1 million parameters for $SU(3)$ Yang--Mills theory on a $16^2$ lattice. This has obvious consequences for training speed and interpretability. It also provides a plausible path for scaling machine-learning approaches toward realistic theories., Comment: 10 pages, 4 figures, 1 table

We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resulting path-gradient estimators are straightforward to implement, have lower variance, and lead not only to faster convergence of training but also to better overall approximation results compared to standard total gradient estimators. We also demonstrate that path-gradient training is less susceptible to mode-collapse. In light of our results, we expect that path-gradient estimators will become the new standard method to train normalizing flows for variational inference., Comment: 29 pages, 8 figures

Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact target distribution. In many applications, this regime can however not be reached by a simple Gaussian variational distribution. In this work, we overcome this crucial limitation by proposing a path-gradient estimator for the considerably more expressive variational family of continuous normalizing flows. We outline an efficient algorithm to calculate this estimator and establish its superior performance empirically., Comment: 8 pages, 5 figures, 39th International Conference on Machine Learning

Counterfactuals can explain classification decisions of neural networks in a human interpretable way. We propose a simple but effective method to generate such counterfactuals. More specifically, we perform a suitable diffeomorphic coordinate transformation and then perform gradient ascent in these coordinates to find counterfactuals which are classified with great confidence as a specified target class. We propose two methods to leverage generative models to construct such suitable coordinate systems that are either exactly or approximately diffeomorphic. We analyze the generation process theoretically using Riemannian differential geometry and validate the quality of the generated counterfactuals using various qualitative and quantitative measures.