An optimal algorithm for stochastic strongly-convex optimization

Abstract

We consider stochastic convex optimization with a strongly convex (but not necessarily smooth) objective. We give an algorithm which performs only gradient updates with optimal rate of convergence.

Cited by in corpus (8)

• Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity
• Asynchronous stochastic convex optimization
• On the Adaptivity of Stochastic Gradient-Based Optimization
• Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization
• Large Scale Markov Decision Processes with Changing Rewards
• Adapting to Function Difficulty and Growth Conditions in Private Optimization
• On Misspecification in Prediction Problems and Robustness via Improper Learning
• Greedy Step Averaging: A parameter-free stochastic optimization method