Publications associées à Strong dual space

Efficient Continual Finite-Sum Minimization

Volkan Cevher, Efstratios Panteleimon Skoulakis, Leello Tadesse Dadi

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

2024

Editing Tetrasubstituted Carbon: Dual C–O Bond Functionalization of Tertiary Alcohols Enabled by Palladium-Based Dyotropic Rearrangement

Qian Wang, Jieping Zhu, Baochao Yang, Tristan Corentin Pierre Delcaillau

Many elegant asymmetric syntheses of enantioenriched tertiary alcohols have been developed, and both the transition metal-catalyzed and the radical-based peripheral functionalization of tertiary alcohols have attracted intensive research interest in recent ...

2024

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 ...

Oxford Univ Press2023

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

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

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

Martin Jaggi, Amirkeivan Mohtashami, Sebastian Urban Stich

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and—in asynchronous implementations—on the gradient staleness. Especially, it has been observed that the spe ...

MICROTOME PUBLISHING2021

Federated Learning Over Wireless Networks: Convergence Analysis and Resource Allocation

Vincent Gramoli

There is an increasing interest in a fast-growing machine learning technique called Federated Learning (FL), in which the model training is distributed over mobile user equipment (UEs), exploiting UEs' local computation and training data. Despite its advan ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Martin Jaggi, Sebastian Urban Stich, Hossein Shokri Ghadikolaei

In distributed optimization, parameter updates from the gradient computing node devices have to be aggregated in every iteration on the orchestrating server. When these updates are sent over an arbitrary commodity network, bandwidth and latency can be limi ...

MICROTOME PUBLISHING2021

A Multi-Agent Primal-Dual Strategy for Composite Optimization over Distributed Features

Ali H. Sayed, Sulaiman A S A E Alghunaim, Ming Yan

This work studies multi-agent sharing optimization problems with the objective function being the sum of smooth local functions plus a convex (possibly non-smooth) function coupling all agents. This scenario arises in many machine learning and engineering ...

IEEE2020

Stochastic Three-Composite Convex Minimization with a Linear Operator

Volkan Cevher

We develop a primal-dual convex minimization framework to solve a class of stochastic convex three-composite problem with a linear operator. We consider the cases where the problem is both convex and strongly convex and analyze the convergence of the propo ...

JMLR: W&CP2018