English
Related papers

Related papers: Thermodynamically Optimal Regularization under Inf…

200 papers

Regularization is a critical component in deep learning. The most commonly used approach, weight decay, applies a constant penalty coefficient uniformly across all parameters. This may be overly restrictive for some parameters, while…

Machine Learning · Computer Science 2024-12-10 Jörg K. H. Franke , Michael Hefenbrock , Gregor Koehler , Frank Hutter

Thermodynamics and information have intricate interrelations. Often thermodynamics is considered to be the logical premise to justify that information is physical - through Landauer's principle -, thereby also linking information and…

Topology optimization is used for the design of high-performance structures but remains fundamentally limited by its iterative nature, requiring repeated finite element analyses that prevent real-time deployment and large-scale design…

Computational Engineering, Finance, and Science · Computer Science 2026-04-07 Aaron Lutheran , Srijan Das , Alireza Tabarraei

Medical image registration aims at identifying the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy. To date, the majority of the deep learning-based registration…

Image and Video Processing · Electrical Eng. & Systems 2023-12-05 Anna Reithmeir , Julia A. Schnabel , Veronika A. Zimmer

A central challenge in cellular signal processing is understanding how biochemical networks perform reliably despite molecular noise. Traditionally, mutual information has been widely used to quantify signaling fidelity, capturing how well…

Biological Physics · Physics 2026-02-23 Mintu Nandi , Sosuke Ito

In this paper we explore the relation between distributionally robust learning and different forms of regularization to enforce robustness of deep neural networks. In particular, starting from a concrete min-max distributionally robust…

Optimization and Control · Mathematics 2022-03-29 Camilo Garcia Trillos , Nicolas Garcia Trillos

Variational regularization is a classical technique to solve statistical inference tasks and inverse problems, with modern data-driven approaches parameterizing regularizers via deep neural networks showcasing impressive empirical…

Machine Learning · Computer Science 2024-09-30 Oscar Leong , Eliza O'Reilly , Yong Sheng Soh

Distributionally Robust Optimization (DRO) has enabled to prove the equivalence between robustness and regularization in classification and regression, thus providing an analytical reason why regularization generalizes well in statistical…

Optimization and Control · Mathematics 2020-07-15 Esther Derman , Shie Mannor

Training and deploying machine learning models that meet fairness criteria for protected groups are fundamental in modern artificial intelligence. While numerous constraints and regularization terms have been proposed in the literature to…

Machine Learning · Computer Science 2024-04-09 Sina Baharlouei , Shivam Patel , Meisam Razaviyayn

This paper investigates, from information theoretic grounds, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact features from data, i.e., using fewer bits than needed to…

Machine Learning · Statistics 2018-11-14 Matías Vera , Leonardo Rey Vega , Pablo Piantanida

Entropy regularized algorithms such as Soft Q-learning and Soft Actor-Critic, recently showed state-of-the-art performance on a number of challenging reinforcement learning (RL) tasks. The regularized formulation modifies the standard RL…

Machine Learning · Statistics 2019-10-15 Elena Smirnova , Elvis Dohmatob

Many recent successes of machine learning went hand in hand with advances in optimization. The exchange of ideas between these fields has worked both ways, with machine learning building on standard optimization procedures such as gradient…

Optimization and Control · Mathematics 2021-10-26 Konstantin Mishchenko

We show how to adjust the parameters of a thermodynamic computer by gradient descent in order to perform a desired computation at a specified observation time. Within a digital simulation of a thermodynamic computer, training proceeds by…

Statistical Mechanics · Physics 2025-09-22 Stephen Whitelam

This paper derives predictive reduced-order models for rocket engine combustion dynamics via Operator Inference, a scientific machine learning approach that blends data-driven learning with physics-based modeling. The non-intrusive nature…

Computational Engineering, Finance, and Science · Computer Science 2021-10-19 Shane A. McQuarrie , Cheng Huang , Karen E. Willcox

We propose a robust and scalable procedure for general optimization and inference problems on manifolds leveraging the classical idea of `median-of-means' estimation. This is motivated by ubiquitous examples and applications in modern data…

Methodology · Statistics 2020-06-16 Lizhen Lin , Drew Lazar , Bayan Sarpabayeva , David B. Dunson

We consider the task of training machine learning models with data-dependent constraints. Such constraints often arise as empirical versions of expected value constraints that enforce fairness or stability goals. We reformulate…

Machine Learning · Statistics 2023-01-18 Songkai Xue , Yuekai Sun , Mikhail Yurochkin

Learning from temporally-correlated data is a core facet of modern machine learning. Yet our understanding of sequential learning remains incomplete, particularly in the multi-trajectory setting where data consists of many independent…

Machine Learning · Computer Science 2025-10-09 Eliot Shekhtman , Yichen Zhou , Ingvar Ziemann , Nikolai Matni , Stephen Tu

The co-optimization of geometry and physical parameters remains challenging in transient multiphysics systems involving moving boundaries, nonlinear material response, phase transitions, and competing objectives. Existing methods often…

Computational Engineering, Finance, and Science · Computer Science 2026-05-05 Navid Zobeiry

Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the…

Machine Learning · Computer Science 2025-05-23 Bang You , Puze Liu , Huaping Liu , Jan Peters , Oleg Arenz

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when…

Machine Learning · Statistics 2024-10-22 Matteo Vilucchio , Nikolaos Tsilivis , Bruno Loureiro , Julia Kempe