Efficient Stochastic Gradient Descent for Learning with Distributionally Robust Optimization
Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore provide a new stochastic gradient descent algorithm to efficiently solve this DRO formulation. Our approach applies gradient descent to the outer minimization formulation and estimates the gradient of the inner maximization based on a sample average approximation. The latter uses a subset of the data in each iteration, progressively increasing the subset size to ensure convergence. Theoretical results include establishing the optimal manner for growing the support size to balance a fundamental tradeoff between stochastic error and computational effort. Empirical results demonstrate the significant benefits of our approach over previous work, and also illustrate how learning with DRO can improve generalization.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences
We develop efficient solution methods for a robust empirical risk minimization problem designed to give calibrated confidence intervals on performance and provide optimal tradeoffs between bias and variance. Our methods …
Nested Stochastic Gradient Descent for (Generalized) Sinkhorn Distance-Regularized Distributionally Robust Optimization
Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled…
Distributionally Time-Varying Online Stochastic Optimization under Polyak-Łojasiewicz Condition with Application in Conditional Value-at-Risk Statistical Learning
In this work, we consider a sequence of stochastic optimization problems following a time-varying distribution via the lens of online optimization. Assuming that the loss function satisfies the Polyak-{\L}ojasiewicz cond…
Stochastic OptimizationStochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust op…
Domain AdaptationDomain GeneralizationMeta-LearningRepresentation Learning+1Sinkhorn Distributionally Robust Optimization
We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributi…