Copertina

A Thermodynamic Theory of Learning Part II: Critical Period Closure and Continual Learning Failure

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Okanohara, Daisuke
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Stochastic Thermodynamics of Learning Parametric Probabilistic Models
di: Parsi, Shervin Sadat
Pubblicazione: (2023)

Thermodynamics of Reinforcement Learning Curricula
di: Adamczyk, Jacob, et al.
Pubblicazione: (2026)

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

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

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

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

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

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

Periodic Regularized Q-Learning
di: Yang, Hyukjun, et al.
Pubblicazione: (2026)

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

A Theory of Machine Learning
di: Kim, Jinsook, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

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

A Theory of Generalization in Deep Learning
di: Litman, Elon, et al.
Pubblicazione: (2026)

Mathematics of Continual Learning
di: Peng, Liangzu, et al.
Pubblicazione: (2025)

Continual Learning on Graphs: A Survey
di: Tian, Zonggui, et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks for Predicting Hydrogen Sorption in Geological Formations: Thermodynamically Constrained Deep Learning Integrating Classical Adsorption Theory
di: Nooraiepour, Mohammad, et al.
Pubblicazione: (2026)

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