SDCA without Duality

Abstract

Stochastic Dual Coordinate Ascent is a popular method for solving regularized loss minimization for the case of convex losses. In this paper we show how a variant of SDCA can be applied for non-convex losses. We prove linear convergence rate even if individual loss functions are non-convex as long as the expected loss is convex.

References in corpus (1)

• A Stochastic Gradient Method with an Exponential Convergence Rate for Finite Training Sets

Cited by in corpus (4)

• Stochastic, Distributed and Federated Optimization for Machine Learning
• Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses
• A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints
• Limitations on Variance-Reduction and Acceleration Schemes for Finite Sum Optimization