English
Related papers

Related papers: Thermodynamically Optimal Regularization under Inf…

200 papers

A robust-to-dynamics optimization (RDO) problem is an optimization problem specified by two pieces of input: (i) a mathematical program (an objective function $f:\mathbb{R}^n\rightarrow\mathbb{R}$ and a feasible set…

Optimization and Control · Mathematics 2023-11-27 Amir Ali Ahmadi , Oktay Gunluk

An optimization framework is presented for minimizing the energy functional developed around a generalized equation governing physical systems such as fluid dynamics, particle transport, phase transition, and other related systems. The…

Fluid Dynamics · Physics 2024-04-25 Varsha Gupta

Thermodynamics and information have intricate inter-relations. The justification of the fact that information is physical, is done by inter-linking information and thermodynamics - through Landauer's principle. This modern approach towards…

Quantum Physics · Physics 2018-05-29 Manabendra Nath Bera , Andreas Winter , Maciej Lewenstein

Learning complex physical dynamics purely from data is challenging due to the intrinsic properties of systems to be satisfied. Incorporating physics-informed priors, such as in Hamiltonian Neural Networks (HNNs), achieves high-precision…

Machine Learning · Computer Science 2024-10-10 Zijie Huang , Wanjia Zhao , Jingdong Gao , Ziniu Hu , Xiao Luo , Yadi Cao , Yuanzhou Chen , Yizhou Sun , Wei Wang

We study the qualitative properties of optimal regularisation parameters in variational models for image restoration. The parameters are solutions of bilevel optimisation problems with the image restoration problem as constraint. A general…

Optimization and Control · Mathematics 2020-02-13 Juan Carlos De Los Reyes , Carola-Bibiane Schönlieb , Tuomo Valkonen

This paper bridges some of the gap between optimal planning and reinforcement learning (RL), both of which share roots in dynamic programming applied to sequential decision making or optimal control. Whereas planning typically favors…

Robotics · Computer Science 2026-03-10 Filip V. Georgiev , Kalle G. Timperi , Başak Sakçak , Steven M. LaValle

Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers…

Machine Learning · Computer Science 2023-11-10 Jiashuo Liu , Jiayun Wu , Tianyu Wang , Hao Zou , Bo Li , Peng Cui

We develop a variational regularisation framework that enables analytical solutions of the stationary de~Broglie--Bohm wave equation. The formulation begins with a Fisher-information-augmented action functional for the probability density…

Quantum Physics · Physics 2026-03-06 Anand Aruna Kumar , S. K. Srivatsa , Rajesh Tengli

Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be…

Machine Learning · Statistics 2020-02-25 Jose Blanchet , Yang Kang , Fan Zhang , Karthyek Murthy

We investigate continuous regularization methods for linear inverse problems of static and dynamic type. These methods are based on dynamic programming approaches for linear quadratic optimal control problems. We prove regularization…

Optimization and Control · Mathematics 2021-01-27 S. Kindermann , A. Leitao

Feature selection identifies subsets of informative features and reduces dimensions in the original feature space, helping provide insights into data generation or a variety of domain problems. Existing methods mainly depend on feature…

Machine Learning · Computer Science 2021-06-07 Xinxing Wu , Qiang Cheng

The rapid scaling of artificial intelligence models has revealed a fundamental tension between model capacity (storage) and inference efficiency (computation). While classical information theory focuses on transmission and storage limits,…

Information Theory · Computer Science 2026-01-01 Jianfeng Xu , Zeyan Li

This paper examines reinforcement learning (RL) in infinite-horizon decision processes with almost-sure safety constraints, crucial for applications like autonomous systems, finance, and resource management. We propose a doubly-regularized…

Machine Learning · Computer Science 2025-09-17 Pekka Malo , Lauri Viitasaari , Antti Suominen , Eeva Vilkkumaa , Olli Tahvonen

3D shape completion is important to enable machines to perceive the complete geometry of objects from partial observations. To address this problem, view-based methods have been presented. These methods represent shapes as multiple depth…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Tao Hu , Zhizhong Han , Matthias Zwicker

We consider the existence of optimal shapes in the context of the thermomechanical system of partial differential equations (PDE) using the recent approach based on elliptic regularity theory. We give an extended and improved definition of…

Optimization and Control · Mathematics 2016-01-05 Laura Bittner , Hanno Gottschalk

Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we present a learning-theoretic framework to quantify the trade-off…

Machine Learning · Statistics 2026-04-02 Amitis Shidani , Tyler Farghly , Yang Sun , Habib Ganjgahi , George Deligiannidis

Regularization-based approaches for injecting constraints in Machine Learning (ML) were introduced to improve a predictive model via expert knowledge. We tackle the issue of finding the right balance between the loss (the accuracy of the…

Machine Learning · Computer Science 2020-05-22 Michele Lombardi , Federico Baldo , Andrea Borghesi , Michela Milano

Stochastic optimisation algorithms are the de facto standard for machine learning with large amounts of data. Handling only a subset of available data in each optimisation step dramatically reduces the per-iteration computational costs,…

Numerical Analysis · Mathematics 2024-12-19 Matthias J. Ehrhardt , Zeljko Kereta , Jingwei Liang , Junqi Tang

Information-processing systems that coordinate multiple agents and objectives face fundamental thermodynamic constraints. We show that solutions with maximum utility to act as coordination focal points have a much higher selection pressure…

Artificial Intelligence · Computer Science 2025-10-16 Atma Anand

Geometric regularity, which leverages data symmetry, has been successfully incorporated into deep learning architectures such as CNNs, RNNs, GNNs, and Transformers. While this concept has been widely applied in robotics to address the curse…

Robotics · Computer Science 2024-03-19 Shengchao Yan , Baohe Zhang , Yuan Zhang , Joschka Boedecker , Wolfram Burgard