English
Related papers

Related papers: Thermodynamic Overfitting and Generalization: Ener…

200 papers

Machine learning models suffer from overfitting, which is caused by a lack of labeled data. To tackle this problem, we proposed a framework of regularization methods, called density-fixing, that can be used commonly for supervised and…

Machine Learning · Computer Science 2020-09-08 Masanari Kimura , Ryohei Izawa

Thermoelectric generation (TEG) has increasingly drawn attention for being environmentally friendly. A few researches have focused on improving TEG efficiency at the system level on vehicle radiators. The most recent reconfiguration…

Other Computer Science · Computer Science 2018-04-06 Hanchen Yang , Feiyang Kang , Caiwen Ding , Ji Li , Jaemin Kim , Donkyu Baek , Shahin Nazarian , Xue Lin , Paul Bogdan , Naehyuck Chang

In this paper, we introduce a physics-driven regularization method for training of deep neural networks (DNNs) for use in engineering design and analysis problems. In particular, we focus on prediction of a physical system, for which in…

Machine Learning · Computer Science 2019-10-17 Mohammad Amin Nabian , Hadi Meidani

While externally driven information engines are well understood, the thermodynamic constraints of their autonomous counterparts remain an open question. Here, we investigate the finite-time operation of an autonomous machine functioning as…

Quantum Physics · Physics 2026-04-20 Wanyan Chen , Miao Chen , Yu-Han Ma

Adaptive physical and biological systems continually process fluctuating information from their environments. When the environment is nonstationary, inference itself becomes a nonequilibrium process with thermodynamic cost. We analyse a…

Statistical Mechanics · Physics 2026-03-23 Aditya Gupta

Global climate models represent small-scale processes such as clouds and convection using quasi-empirical models known as parameterizations, and these parameterizations are a leading cause of uncertainty in climate projections. A promising…

Atmospheric and Oceanic Physics · Physics 2020-08-31 Janni Yuval , Paul A. O'Gorman

We propose a regularization framework inspired by thermodynamic work for guiding pre-trained probability flow generative models (e.g., continuous normalizing flows or diffusion models) by minimizing excess work, a concept rooted in…

We develop a statistical mechanical interpretation of algorithmic information theory by introducing the notion of thermodynamic quantities, such as free energy, energy, statistical mechanical entropy, and specific heat, into algorithmic…

Information Theory · Computer Science 2009-04-09 Kohtaro Tadaki

In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; however, fewer studies…

Human-Computer Interaction · Computer Science 2018-03-12 Pedram Daee , Tomi Peltola , Aki Vehtari , Samuel Kaski

While there are many studies on weight regularization, the study on structure regularization is rare. Many existing systems on structured prediction focus on increasing the level of structural dependencies within the model. However, this…

Machine Learning · Computer Science 2015-02-02 Xu Sun

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

Machine Learning · Computer Science 2025-04-16 Alexander David Goldie , Chris Lu , Matthew Thomas Jackson , Shimon Whiteson , Jakob Nicolaus Foerster

We propose a physics-based regularization technique for function learning, inspired by statistical mechanics. By drawing an analogy between optimizing the parameters of an interpolator and minimizing the energy of a system, we introduce…

Machine Learning · Computer Science 2025-08-20 Abhisek Ganguly , Alessandro Gabbana , Vybhav Rao , Sauro Succi , Santosh Ansumali

Thermodynamics establishes that information acquired through measurement can be converted into work, as exemplified by Maxwell's demon and Szilard engines. Most experimental realizations of information engines, however, implicitly assume…

Soft Condensed Matter · Physics 2026-03-09 Lokesh Muruga , Felix Ginot , Sarah A. M. Loos , Clemens Bechinger

We consider electricity capacity expansion models, which optimize investment and retirement decisions by minimizing both investment and operation costs. In order to provide credible support for planning and policy decisions, these models…

Optimization and Control · Mathematics 2025-01-08 Filippo Pecci , Jesse D. Jenkins

While there are many works on the applications of machine learning, not so many of them are trying to understand the theoretical justifications to explain their efficiency. In this work, overfitting control (or generalization property) in…

Machine Learning · Computer Science 2024-12-17 Sergei V. Kozyrev , Ilya A Lopatin , Alexander N Pechen

The reliability of machine learning (ML) software systems is heavily influenced by changes in data over time. For that reason, ML systems require regular maintenance, typically based on model retraining. However, retraining requires…

Machine Learning · Computer Science 2025-06-18 Lorena Poenaru-Olaru , June Sallou , Luis Cruz , Jan Rellermeyer , Arie van Deursen

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…

Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees…

Machine Learning · Computer Science 2025-06-10 Firas Laakom , Haobo Chen , Jürgen Schmidhuber , Yuheng Bu

We try to establish a unified information theoretic approach to learning and to explore some of its applications. First, we define {\em predictive information} as the mutual information between the past and the future of a time series,…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Ilya Nemenman

Systems that are driven by a randomly timed, external protocol can seemingly violate the second law of thermodynamics. We show that this thermodynamic paradox is resolved if the outcome of the random time is stored in a memory device.…

Statistical Mechanics · Physics 2025-10-28 Izaak Neri