Skip to yearly menu bar Skip to main content


Poster

A PAC-Bayesian Analysis of Randomized Learning with Application to Stochastic Gradient Descent

Ben London

Pacific Ballroom #212

Keywords: [ Learning Theory ] [ Stochastic Methods ] [ Optimization ]


Abstract:

We study the generalization error of randomized learning algorithms -- focusing on stochastic gradient descent (SGD) -- using a novel combination of PAC-Bayes and algorithmic stability. Importantly, our generalization bounds hold for all posterior distributions on an algorithm's random hyperparameters, including distributions that depend on the training data. This inspires an adaptive sampling algorithm for SGD that optimizes the posterior at runtime. We analyze this algorithm in the context of our generalization bounds and evaluate it on a benchmark dataset. Our experiments demonstrate that adaptive sampling can reduce empirical risk faster than uniform sampling while also improving out-of-sample accuracy.

Live content is unavailable. Log in and register to view live content