paper-with-me

홈 › Papers

Generalization Bounds for Dependent Data using Online-to-Batch Conversion

2024-05-22 · Sagnik Chatterjee, Manuj Mukherjee, Alhad Sethi

In this work, we give generalization bounds of statistical learning algorithms trained on samples drawn from a dependent data source, both in expectation and with high probability, using the Online-to-Batch conversion paradigm. We show that the generalization error of statistical learners in the dependent data setting is equivalent to the generalization error of statistical learners in the i.i.d. setting up to a term that depends on the decay rate of the underlying mixing stochastic process and is independent of the complexity of the statistical learner. Our proof techniques involve defining a new notion of stability of online learning algorithms based on Wasserstein distances and employing "near-martingale" concentration bounds for dependent random variables to arrive at appropriate upper bounds for the generalization error of statistical learners trained on dependent data.

📄 PDF Abstract BibTeX arXiv:2405.13666

Code (0)

등록된 구현이 없습니다.

Tasks

Generalization Bounds

Similar Papers 제목 키워드 기반

Information-Theoretic Generalization Bounds for Sequential Decision Making

2026-05-12 · Futoshi Futami, Masahiro Fujisawa arxiv

Information-theoretic generalization bounds based on the supersample construction are a central tool for algorithm-dependent generalization analysis in the batch i.i.d.~setting. However, existing supersample conditional …

Multi-Armed BanditsDecision MakingActive Learning

Select without Fear: Almost All Mini-Batch Schedules Generalize Optimally

2023-05-03 · Konstantinos E. Nikolakakis, Amin Karbasi, Dionysis Kalogerias

We establish matching upper and lower generalization error bounds for mini-batch Gradient Descent (GD) training with either deterministic or stochastic, data-independent, but otherwise arbitrary batch selection rules. We…

All

Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed Bandit Problem

2019-05-08 · Nadav Merlis, Shie Mannor

We consider the combinatorial multi-armed bandit (CMAB) problem, where the reward function is nonlinear. In this setting, the agent chooses a batch of arms on each round and receives feedback from each arm of the batch. …

Black-Box Generalization: Stability of Zeroth-Order Learning

2022-02-14 · Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias, Amin Karbasi

We provide the first generalization error analysis for black-box learning through derivative-free optimization. Under the assumption of a Lipschitz and smooth unknown loss, we consider the Zeroth-order Stochastic Search …

Generalization Bounds

Online PAC-Bayes Learning

2022-05-31 · Maxime Haddouche, Benjamin Guedj

Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning problems where data streams are collect…