Stochastic Dual Coordinate Ascent with Adaptive Probabilities

Abstract

This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method adaptively change the probability distribution over the dual variables throughout the iterative process. AdaSDCA achieves provably better complexity bound than SDCA with the best fixed probability distribution, known as importance sampling. However, it is of a theoretical character as it is expensive to implement. We also propose AdaSDCA+: a practical variant which in our experiments outperforms existing non-adaptive methods.

References in corpus (8)

• No More Pesky Learning Rates
• Communication-Efficient Distributed Dual Coordinate Ascent
• Mini-Batch Primal and Dual Methods for SVMs
• Proximal Stochastic Dual Coordinate Ascent
• Randomized Dual Coordinate Ascent with Arbitrary Sampling
• An Accelerated Proximal Coordinate Gradient Method and its Application to Regularized Empirical Risk Minimization
• Coordinate Descent with Arbitrary Sampling I: Algorithms and Complexity
• Robust Block Coordinate Descent

Cited by in corpus (6)

• Stochastic Distributed Learning with Gradient Quantization and Variance Reduction
• Primal Method for ERM with Flexible Mini-batching Schemes and Non-convex Losses
• Privacy Preserving Randomized Gossip Algorithms
• Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop
• Randomized Iterative Methods for Linear Systems: Momentum, Inexactness and Gossip
• Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters