On The Convergence Of Stochastic Primal-Dual Hybrid Gradient

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for instance, in federated learning. Various schemes have been designed to compress the model updates in orde ...

Universal methods for optimization are designed to achieve theoretically optimal convergence rates without any prior knowledge of the problem’s regularity parameters or the accurarcy of the gradient oracle employed by the optimizer. In this regard, existin ...

There has been a recent surge of interest in the study of asymptotic reconstruction performance in various cases of generalized linear estimation problems in the teacher-student setting, especially for the case of i.i.d standard normal matrices. Here, we g ...

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical ...

The alkali-silica reaction (ASR), also known as concrete cancer, is one of the most prevalent causes of concrete degradation. In this chemical reaction, amorphous silica in the aggregates reacts with alkalis in the pore solution. By absorbing water, hydrop ...

We develop a novel 2D functional learning framework that employs a sparsity-promoting regularization based on second-order derivatives. Motivated by the nature of the regularizer, we restrict the search space to the span of piecewise-linear box splines shi ...

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and then o ...

We propose an adaptive variance-reduction method, called AdaSpider, for minimization of L-smooth, non-convex functions with a finite-sum structure. In essence, AdaSpider combines an AdaGrad-inspired [Duchi et al., 2011, McMahan & Streeter, 2010], but a fai ...

In this paper, we formulate a mixed integer linear program (MILP) for the simulated maximum likelihood estimation (MLSE) problem and devise a Benders decomposition approach to speed up the solution process. This framework can be applied to any advanced dis ...

On The Convergence Of Stochastic Primal-Dual Hybrid Gradient

Chat with Graph Search

Stochastic distributed learning with gradient quantization and double-variance reduction

UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees

Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (Or: How to Prove Kabashima’s Replica Formula)

An Accelerated First-Order Method for Non-convex Optimization on Manifolds

Efficient Meso-Scale Modeling of Alkali-Silica-Reaction Damage in Concrete

Learning of Continuous and Piecewise-Linear Functions With Hessian Total-Variation Regularization

Proximal Point Imitation Learning

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

A Benders decomposition for maximum simulated likelihood estimation of advanced discrete choice models