:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Author:	Okanohara, Daisuke
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2602.07950
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Thermodynamic Theory of Learning I: Irreversible Ensemble Transport and Epistemic Costs
by: Okanohara, Daisuke
Published: (2026)

Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport
by: Ikeda, Kotaro, et al.
Published: (2024)

Generative Model for Constructing Reaction Path from Initial to Final States
by: Hayashi, Akihide, et al.
Published: (2024)

On the Occurence of Critical Learning Periods in Neural Networks
by: Pawlak, Stanisław
Published: (2025)

One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks
by: Fukase, Vinicius Yuiti, et al.
Published: (2025)

When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
by: Higuchi, Rei, et al.
Published: (2025)

Machine Learning for Improved Density Functional Theory Thermodynamics
by: Simak, Sergei I., et al.
Published: (2025)

Critical Learning Periods Emerge Even in Deep Linear Networks
by: Kleinman, Michael, et al.
Published: (2023)

Refining Machine Learning Potentials through Thermodynamic Theory of Phase Transitions
by: Fuchs, Paul, et al.
Published: (2025)

From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM
by: Fink, Olga, et al.
Published: (2025)

Theory on Mixture-of-Experts in Continual Learning
by: Li, Hongbo, et al.
Published: (2024)

Hierarchical Inference and Closure Learning via Adaptive Surrogates for ODEs and PDEs
by: Zhang, Pengyu, et al.
Published: (2026)

A Statistical Theory of Regularization-Based Continual Learning
by: Zhao, Xuyang, et al.
Published: (2024)

Broad Critic Deep Actor Reinforcement Learning for Continuous Control
by: Thalagala, Shiron, et al.
Published: (2024)

Thermodynamics of Reinforcement Learning Curricula
by: Adamczyk, Jacob, et al.
Published: (2026)

The Machine Learning Approach to Moment Closure Relations for Plasma: A Review
by: Burles, Samuel, et al.
Published: (2025)

Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
by: Lim, Wonseon, et al.
Published: (2026)

Information as Structural Alignment: A Dynamical Theory of Continual Learning
by: Negulescu, Radu
Published: (2026)

Analysis of Diagnostics (Part II): Prevalence, Linear Independence, and Unsupervised Learning
by: Patrone, Paul N., et al.
Published: (2024)

Predicting Channel Closures in the Lightning Network with Machine Learning
by: Antonelli, Simone, et al.
Published: (2026)

Differentiable Thermodynamic Phase-Equilibria for Machine Learning
by: Hicham, Karim K. Ben, et al.
Published: (2026)

Stochastic Thermodynamics of Learning Parametric Probabilistic Models
by: Parsi, Shervin Sadat
Published: (2023)

On the Theory of Continual Learning with Gradient Descent for Neural Networks
by: Taheri, Hossein, et al.
Published: (2025)

Periodic Regularized Q-Learning
by: Yang, Hyukjun, et al.
Published: (2026)

Inferential Mechanics Part 1: Causal Mechanistic Theories of Machine Learning in Chemical Biology with Implications
by: Balabin, Ilya, et al.
Published: (2026)

Quantile Online Learning for Semiconductor Failure Analysis
by: Zhou, Bangjian, et al.
Published: (2023)

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control
by: Alzorgan, Hazim, et al.
Published: (2025)

Dissecting the Failure of Invariant Learning on Graphs
by: Wang, Qixun, et al.
Published: (2024)

Neural Functions for Learning Periodic Signal
by: Cho, Woojin, et al.
Published: (2025)

A Theory of Machine Learning
by: Kim, Jinsook, et al.
Published: (2024)

Machine Learning Coarse-Grained Potentials of Protein Thermodynamics
by: Majewski, Maciej, et al.
Published: (2022)

Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data
by: Heimbach, Lothar, et al.
Published: (2025)

Boltzmann Classifier: A Thermodynamic-Inspired Approach to Supervised Learning
by: Amin, Muhamed, et al.
Published: (2025)

Statistical Theory of Multi-stage Newton Iteration Algorithm for Online Continual Learning
by: Lu, Xinjia, et al.
Published: (2025)

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
by: Patel, Nyal, et al.
Published: (2025)

Learning from Failures in Multi-Attempt Reinforcement Learning
by: Chung, Stephen, et al.
Published: (2025)

Counterfactual Explanations of Black-box Machine Learning Models using Causal Discovery with Applications to Credit Rating
by: Takahashi, Daisuke, et al.
Published: (2024)

A Study of Continual Learning Methods for Q-Learning
by: Bagus, Benedikt, et al.
Published: (2022)

Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning
by: Fischer, Paul, et al.
Published: (2025)

A Comprehensive Survey of Continual Learning: Theory, Method and Application
by: Wang, Liyuan, et al.
Published: (2023)