Publications related to Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Understanding generalization and robustness in modern deep learning

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Universal and adaptive methods for robust stochastic optimization

Ali Kavis

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

EPFL2023

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

Mehmet Fatih Sahin

Non-convex constrained optimization problems have become a powerful framework for modeling a wide range of machine learning problems, with applications in k-means clustering, large- scale semidefinite programs (SDPs), and various other tasks. As the perfor ...

EPFL2023

The statistical complexity of early-stopped mirror descent

Tomas Vaskevicius, Varun Kanade

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

Oxford2023

Stochastic homogenization of degenerate integral functionals with linear growth

Matthias Ruf

We study the limit behaviour of sequences of non-convex, vectorial, random integral functionals, defined on W1,1, whose integrands are ergodic and satisfy degenerate linear growth conditions. The latter involve suitable random, scale-dependent weight-funct ...

2023

Stochastic distributed learning with gradient quantization and double-variance reduction

Sebastian Urban Stich, Konstantin Mishchenko

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 ...

TAYLOR & FRANCIS LTD2022

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

Volkan Cevher, Kimon Antonakopoulos, Efstratios Panteleimon Skoulakis, Leello Tadesse Dadi, Ali Kavis

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 ...

2022

Metrizing Fairness

Daniel Kuhn, Yves Rychener, Bahar Taskesen

We study supervised learning problems for predicting properties of individuals who belong to one of two demographic groups, and we seek predictors that are fair according to statistical parity. This means that the distributions of the predictions within th ...

2022

A first-order primal-dual method with adaptivity to local smoothness

Volkan Cevher, Maria-Luiza Vladarean

We consider the problem of finding a saddle point for the convex-concave objective

\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)

, where

f

is a convex function with locally Lipschitz gradient and

g

is convex and possibly non-smooth. We propose an ...

2021

Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond

Ahmet Alacaoglu

Stochastic gradient descent (SGD) and randomized coordinate descent (RCD) are two of the workhorses for training modern automated decision systems. Intriguingly, convergence properties of these methods are not well-established as we move away from the spec ...

EPFL2021

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Graph Chatbot

Chat with Graph Search

Understanding generalization and robustness in modern deep learning

Universal and adaptive methods for robust stochastic optimization

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

The statistical complexity of early-stopped mirror descent

Stochastic homogenization of degenerate integral functionals with linear growth

Stochastic distributed learning with gradient quantization and double-variance reduction

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

Metrizing Fairness

A first-order primal-dual method with adaptivity to local smoothness

Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond

Universal and adaptive methods for robust stochastic optimization

Understanding generalization and robustness in modern deep learning

Stochastic distributed learning with gradient quantization and double-variance reduction

Metrizing Fairness

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

Stochastic homogenization of degenerate integral functionals with linear growth

Augmented Lagrangian Methods for Provable and Scalable Machine Learning

A first-order primal-dual method with adaptivity to local smoothness

Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond

The statistical complexity of early-stopped mirror descent