A framework for bilevel optimization that enables stochastic and global variance reduction algorithms

arXiv2201.13409MaRDI QIDQ6389748

Author name not available (Why is that?)

Publication date: 31 January 2022

Abstract: Bilevel optimization, the problem of minimizing a value function which involves the arg-minimum of another function, appears in many areas of machine learning. In a large scale empirical risk minimization setting where the number of samples is huge, it is crucial to develop stochastic methods, which only use a few samples at a time to progress. However, computing the gradient of the value function involves solving a linear system, which makes it difficult to derive unbiased stochastic estimates. To overcome this problem we introduce a novel framework, in which the solution of the inner problem, the solution of the linear system, and the main variable evolve at the same time. These directions are written as a sum, making it straightforward to derive unbiased estimates. The simplicity of our approach allows us to develop global variance reduction algorithms, where the dynamics of all variables is subject to variance reduction. We demonstrate that SABA, an adaptation of the celebrated SAGA algorithm in our framework, has $O(frac1T)$ convergence rate, and that it achieves linear convergence under Polyak-Lojasciewicz assumption. This is the first stochastic algorithm for bilevel optimization that verifies either of these properties. Numerical experiments validate the usefulness of our method.

Has companion code repository: https://github.com/benchopt/benchmark_bilevel

This page was built for publication: A framework for bilevel optimization that enables stochastic and global variance reduction algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6389748)