paper-with-me

홈 › Papers

Fluctuation-dissipation Type Theorem in Stochastic Linear Learning

2021-06-04 · Manhyung Han, Jeonghyeok Park, Taewoong Lee, Jung Hoon Han

The fluctuation-dissipation theorem (FDT) is a simple yet powerful consequence of the first-order differential equation governing the dynamics of systems subject simultaneously to dissipative and stochastic forces. The linear learning dynamics, in which the input vector maps to the output vector by a linear matrix whose elements are the subject of learning, has a stochastic version closely mimicking the Langevin dynamics when a full-batch gradient descent scheme is replaced by that of stochastic gradient descent. We derive a generalized FDT for the stochastic linear learning dynamics and verify its validity among the well-known machine learning data sets such as MNIST, CIFAR-10 and EMNIST.

📄 PDF Abstract BibTeX arXiv:2106.02220

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Type Prediction

Similar Papers 제목 키워드 기반

Predicting Forced Responses of Probability Distributions via the Fluctuation-Dissipation Theorem and Generative Modeling

2025-04-17 · Ludovico T. Giorgini, Fabrizio Falasca, Andre N. Souza

We present a novel data-driven framework for estimating the response of higher-order moments of nonlinear stochastic systems to small external perturbations. The classical Generalized Fluctuation-Dissipation Theorem (GFD…

Fluctuation without dissipation: Microcanonical Langevin Monte Carlo

2023-03-31 · Jakob Robnik, Uroš Seljak

Stochastic sampling algorithms such as Langevin Monte Carlo are inspired by physical systems in a heat bath. Their equilibrium distribution is the canonical ensemble given by a prescribed target distribution, so they mus…

Broken Ergodicity and the Violation of the Fluctuation-Dissipation Theorem Lead to Generalization Beyond Overfitting in Machine Learning

2026-07-05 · Chan Li, Nigel Goldenfeld arxiv

The remarkable ability of modern neural networks to generalize improves with increasing network capacity, even when the number of model parameters or effective degrees of freedom exceeds the number of training data point…

Response Theory via Generative Score Modeling

2024-02-01 · Ludovico Theo Giorgini, Katherine Deck, Tobias Bischoff, Andre Souza

We introduce an approach for analyzing the responses of dynamical systems to external perturbations that combines score-based generative modeling with the Generalized Fluctuation-Dissipation Theorem (GFDT). The methodolo…

Time Series

Fluctuation-dissipation relations for stochastic gradient descent

2018-09-28 · ICLR 2019 5 · Sho Yaida

The notion of the stationary equilibrium ensemble has played a central role in statistical mechanics. In machine learning as well, training serves as generalized equilibration that drives the probability distribution of …

BIG-bench Machine Learning