Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization

Abstract

We consider the problem of minimizing the sum of two convex functions: one is differentiable and relatively smooth with respect to a reference convex function, and the other can be nondifferentiable but simple to optimize. We investigate a triangle scaling property of the Bregman distance generated by the reference convex function and present accelerated Bregman proximal gradient (ABPG) methods that attain an $O(k^{-\gamma })$ convergence rate, where $\gamma \in (0,2]$ is the triangle scaling exponent (TSE) of the Bregman distance. For the Euclidean distance, we have $\gamma =2$ and recover the convergence rate of Nesterov's accelerated gradient methods. For non-Euclidean Bregman distances, the TSE can be much smaller (say $\gamma \le 1$), but we show that a relaxed definition of intrinsic TSE is always equal to 2. We exploit the intrinsic TSE to develop adaptive ABPG methods that converge much faster in practice. Although theoretical guarantees on a fast convergence rate seem to be out of reach in general, our methods obtain empirical $O(k^{-2})$ rates in numerical experiments on several applications and provide posterior numerical certificates for the fast rates.

References in corpus (1)

• "Relative-Continuity" for Non-Lipschitz Non-Smooth Convex Optimization using Stochastic (or Deterministic) Mirror Descent

Cited by in corpus (15)

• A Bregman forward-backward linesearch algorithm for nonconvex composite optimization: superlinear convergence to nonisolated local minima
• Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
• Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms
• Multi-block Bregman proximal alternating linearized minimization and its application to orthogonal nonnegative matrix factorization
• Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization
• Advances in Asynchronous Parallel and Distributed Optimization
• Bregman Augmented Lagrangian and Its Acceleration
• Local convexity of the TAP free energy and AMP convergence for Z2-synchronization
• Sinkhorn Algorithm as a Special Case of Stochastic Mirror Descent
• Bregman Proximal Gradient Algorithm with Extrapolation for a class of Nonconvex Nonsmooth Minimization Problems
• Adaptive first-order methods revisited: Convex optimization without Lipschitz requirements
• A Study of Condition Numbers for First-Order Optimization
• First-Order Algorithms Without Lipschitz Gradient: A Sequential Local Optimization Approach
• Robust Data-Driven Accelerated Mirror Descent
• Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters