Riemannian Stochastic Approximation for Minimizing Tame Nonsmooth Objective Functions
In many learning applications, the parameters in a model are structurally constrained in a way that can be modeled as them lying on a Riemannian manifold. Riemannian optimization, wherein procedures to enforce an iterative minimizing sequence to be constrained to the manifold, is used to train such models. At the same time, tame geometry has become a significant topological description of nonsmooth functions that appear in the landscapes of training neural networks and other important models with structural compositions of continuous nonlinear functions with nonsmooth maps. In this paper, we study the properties of such stratifiable functions on a manifold and the behavior of retracted stochastic gradient descent, with diminishing stepsizes, for minimizing such functions.
Code (0)
등록된 구현이 없습니다.
Tasks
Riemannian optimizationSimilar Papers 제목 키워드 기반
Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold
Riemannian optimization has drawn a lot of attention due to its wide applications in practice. Riemannian stochastic first-order algorithms have been studied in the literature to solve large-scale machine learning proble…
Low-Rank Matrix CompletionMatrix CompletionRiemannian optimizationFinite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds
This work addresses the finite-time analysis of nonsmooth nonconvex stochastic optimization under Riemannian manifold constraints. We adapt the notion of Goldstein stationarity to the Riemannian setting as a performance …
Stochastic OptimizationDeep Learning as the Disciplined Construction of Tame Objects
One can see deep-learning models as compositions of functions within the so-called tame geometry. In this expository note, we give an overview of some topics at the interface of tame geometry (also known as o-minimality)…
Piecewise Polynomial Regression of Tame Functions via Integer Programming
Tame functions are a class of nonsmooth, nonconvex functions, which feature in a wide range of applications: functions encountered in the training of deep neural networks with all common activations, value functions of m…
regressionMISSO: Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex and Nonsmooth Problems
Many constrained, nonconvex and nonsmooth optimization problems can be tackled using the majorization-minimization (MM) method which alternates between constructing a surrogate function which upper bounds the objective f…
Variational Inference