English
Related papers

Related papers: $\alpha$-divergence Improves the Entropy Productio…

200 papers

Bayesian Neural Networks (BNNs) are trained to optimize an entire distribution over their weights instead of a single set, having significant advantages in terms of, e.g., interpretability, multi-task learning, and calibration. Because of…

Machine Learning · Computer Science 2022-10-07 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Data collection is a critical step in statistical inference and data science, and the goal of statistical experimental design (ED) is to find the data collection setup that can provide most information for the inference. In this work we…

Computation · Statistics 2020-07-01 Ziqiao Ao , Jinglai Li

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

The maximum entropy principle (MEP) apparently allows us to derive, or justify, fundamental results of equilibrium statistical mechanics. Because of this, a school of thought considers the MEP as a powerful and elegant way to make…

Statistical Mechanics · Physics 2015-12-09 Gennaro Auletta , Lamberto Rondoni , Angelo Vulpiani

The concept of attention, numerical weights that emphasize the importance of particular data, has proven to be very relevant in artificial intelligence. Relative entropy (RE, aka Kullback-Leibler divergence) plays a central role in…

Information Theory · Computer Science 2024-01-10 Torsten Enßlin , Carolin Weidinger , Philipp Frank

We consider the problem of learning a loss function which, when minimized over a training dataset, yields a model that approximately minimizes a validation error metric. Though learning an optimal loss function is NP-hard, we present an…

Machine Learning · Computer Science 2019-07-02 Matthew Streeter

Statistical divergences (SDs), which quantify the dissimilarity between probability distributions, are a basic constituent of statistical inference and machine learning. A modern method for estimating those divergences relies on…

Statistics Theory · Mathematics 2022-03-30 Sreejith Sreekumar , Ziv Goldfeld

This dissertation makes three main contributions. First, We identify a new connection between policy gradient and dynamic programming in MMDPs and propose the Coordinate Ascent Dynamic Programming (CADP) algorithm to compute a Markov policy…

Machine Learning · Computer Science 2025-10-21 Xihong Su

The performance of machine learning classification algorithms are evaluated by estimating metrics, often from the confusion matrix, using training data and cross-validation. However, these do not prove that the best possible performance has…

Machine Learning · Statistics 2024-03-05 L. Crow , S. J. Watts

Energy-based models are a simple yet powerful class of probabilistic models, but their widespread adoption has been limited by the computational burden of training them. We propose a novel loss function called Energy Discrepancy (ED) which…

Machine Learning · Statistics 2023-11-28 Tobias Schröder , Zijing Ou , Jen Ning Lim , Yingzhen Li , Sebastian J. Vollmer , Andrew B. Duncan

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Machine Learning · Computer Science 2019-07-15 Farshid Varno , Behrouz Haji Soleimani , Marzie Saghayi , Lisa Di Jorio , Stan Matwin

Many scientific and engineering problems require accurate models of dynamical systems with rare and extreme events. Such problems present a challenging task for data-driven modelling, with many naive machine learning methods failing to…

Machine Learning · Computer Science 2021-12-03 Samuel Rudy , Themistoklis Sapsis

Active systems comprise a class of nonequilibrium dynamics in which individual components autonomously dissipate energy. Efforts towards understanding the role played by activity have centered on computation of the entropy production rate…

Statistical Mechanics · Physics 2024-11-22 Nicholas M. Boffi , Eric Vanden-Eijnden

We consider the numerical integration of conservation laws endowed with an entropy inequality and we study the residual of the scheme on this inequality, which represents the numerical entropy production. This idea has been introduced and…

Numerical Analysis · Mathematics 2025-11-19 Matteo Semplice , Alessandra Zappa

Deep Learning predictions with measurable confidence are increasingly desirable for real-world problems, especially in high-risk settings. The Conformal Prediction (CP) framework is a versatile solution that guarantees a maximum error rate…

Machine Learning · Computer Science 2023-08-08 Julia A. Meister , Khuong An Nguyen , Stelios Kapetanakis , Zhiyuan Luo

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-01 Shihao Zhang , Linlin Yang , Michael Bi Mi , Xiaoxu Zheng , Angela Yao

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Machine Learning · Computer Science 2025-05-22 Shivam Agarwal , Zimin Zhang , Lifan Yuan , Jiawei Han , Hao Peng

An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo…

Machine Learning · Computer Science 2022-11-23 Anthony Corso , Kyu-Young Kim , Shubh Gupta , Grace Gao , Mykel J. Kochenderfer

The ability to continuously learn remains elusive for deep learning models. Unlike humans, models cannot accumulate knowledge in their weights when learning new tasks, mainly due to an excess of plasticity and the low incentive to reuse…

Machine Learning · Computer Science 2022-04-21 Vladimir Araujo , Julio Hurtado , Alvaro Soto , Marie-Francine Moens

Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models perform well on training data but have poor prediction accuracy for minority…

Machine Learning · Computer Science 2025-02-17 Tao Wen , Zihan Wang , Quan Zhang , Qi Lei