paper-with-me

Papers

Understanding the Generalization Error of Markov algorithms through Poissonization

2025-02-11 · Benjamin Dupuis, Maxime Haddouche, George Deligiannidis, Umut Simsekli

Using continuous-time stochastic differential equation (SDE) proxies to stochastic optimization algorithms has proven fruitful for understanding their generalization abilities. A significant part of these approaches are based on the so-called `entropy flows'', which greatly simplify the generalization analysis. Unfortunately, such well-structured entropy flows cannot be obtained for most discrete-time algorithms, and the existing SDE approaches remain limited to specific noise and algorithmic structures. We aim to alleviate this issue by introducing a generic framework for analyzing the generalization error of Markov algorithms through Poissonization', a continuous-time approximation of discrete-time processes with formal approximation guarantees. Through this approach, we first develop a novel entropy flow, which directly leads to PAC-Bayesian generalization bounds. We then draw novel links to modified versions of the celebrated logarithmic Sobolev inequalities (LSI), identify cases where such LSIs are satisfied, and obtain improved bounds. Beyond its generality, our framework allows exploiting specific properties of learning algorithms. In particular, we incorporate the noise structure of different algorithm types - namely, those with additional noise injections (noisy) and those without (non-noisy) - through various technical tools. This illustrates the capacity of our methods to achieve known (yet, Poissonized) and new generalization bounds.

📄 PDF Abstract BibTeX arXiv:2502.07584

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization BoundsStochastic Optimization

Similar Papers 제목 키워드 기반

Generalization Error Bounds on Deep Learning with Markov Datasets

2021-12-23 · Lan V. Truong

In this paper, we derive upper bounds on generalization errors for deep neural networks with Markov datasets. These bounds are developed based on Koltchinskii and Panchenko's approach for bounding the generalization erro…

Deep Learning

Generalization Error Bounds for Noisy, Iterative Algorithms

2018-01-12 · Ankit Pensia, Varun Jog, Po-Ling Loh

In statistical learning theory, generalization error is used to quantify the degree to which a supervised machine learning algorithm may overfit to training data. Recent work [Xu and Raginsky (2017)] has established a bo…

Learning Theory

Stability of Stochastic Approximations with `Controlled Markov' Noise and Temporal Difference Learning

2015-04-23 · Arunselvan Ramaswamy, Shalabh Bhatnagar

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many rei…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay

2024-01-03 · Yicheng Li, Weiye Gan, Zuoqiang Shi, Qian Lin

The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice of the regularization parameter rather …

regression

Information-Theoretic Bounds on the Moments of the Generalization Error of Learning Algorithms

2021-02-03 · Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues

Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical…

BIG-bench Machine Learning