$L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

Published: 21 Sept 2023, Last Modified: 14 Jan 2024NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Uniform stability, Randomized learning algorithms, Confidence boosting, Generalization bounds, Stochastic gradient methods
TL;DR: We introduce a novel concept of $L_2$-uniform stability and prove a set of sharper exponential generalization bounds for randomized learning algorithms using confidence boosting techniques.
Abstract: Exponential generalization bounds with near-optimal rates have recently been established for uniformly stable algorithms~\citep{feldman2019high,bousquet2020sharper}. We seek to extend these best known high probability bounds from deterministic learning algorithms to the regime of randomized learning. One simple approach for achieving this goal is to define the stability for the expectation over the algorithm's randomness, which may result in sharper parameter but only leads to guarantees regarding the on-average generalization error. Another natural option is to consider the stability conditioned on the algorithm's randomness, which is way more stringent but may lead to generalization with high probability jointly over the randomness of sample and algorithm. The present paper addresses such a tension between these two alternatives and makes progress towards relaxing it inside a classic framework of confidence-boosting. To this end, we first introduce a novel concept of $L_2$-uniform stability that holds uniformly over data but in second-moment over the algorithm's randomness. Then as a core contribution of this work, we prove a strong exponential bound on the first-moment of generalization error under the notion of $L_2$-uniform stability. As an interesting consequence of the bound, we show that a bagging-based meta algorithm leads to near-optimal generalization with high probability jointly over the randomness of data and algorithm. We further substantialize these generic results to stochastic gradient descent (SGD) to derive sharper exponential bounds for convex or non-convex optimization with natural time-decaying learning rates, which have not been possible to prove with the existing stability-based generalization guarantees.
Supplementary Material: pdf
Submission Number: 5578