Skip to yearly menu bar Skip to main content


Talk
in
Workshop: OPT2020: Optimization for Machine Learning

Contributed Video: Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization, Samuel Horvath

Samuel Horváth


Abstract:

Adaptivity is an important yet under-studied property in modern optimization theory. The gap between the state-of-the-art theory and the current practice is striking in that algorithms with desirable theoretical guarantees typically involve drastically different settings of hyperparameters, such as step-size schemes and batch sizes, in different regimes. Despite the appealing theoretical results, such divisive strategies provide little, if any, insight to practitioners to select algorithms that work broadly without tweaking the hyperparameters. In this work, blending the ``geometrization'' technique introduced by \cite{lei2016less} and the \texttt{SARAH} algorithm of \cite{nguyen2017sarah}, we propose the Geometrized \texttt{SARAH} algorithm for non-convex finite-sum and stochastic optimization. Our algorithm is proved to achieve adaptivity to both the magnitude of the target accuracy and the Polyak-\L{}ojasiewicz (PL) constant, if present. In addition, it achieves the best-available convergence rate for non-PL objectives simultaneously while outperforming existing algorithms for PL objectives.