research
∙
08/29/2023
The Relative Gaussian Mechanism and its Application to Private Gradient Descent
The Gaussian Mechanism (GM), which consists in adding Gaussian noise to ...
share
research
∙
05/02/2023
Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees
Gradient clipping is a popular modification to standard (stochastic) gra...
research
∙
01/05/2023
Beyond spectral gap (extended): The role of the topology in decentralized learning
In data-parallel optimization of machine learning models, workers collab...
research
∙
06/07/2022
Beyond spectral gap: The role of the topology in decentralized learning
In data-parallel optimization of machine learning models, workers collab...
research
∙
05/30/2022
A principled framework for the design and analysis of token algorithms
We consider a decentralized optimization problem, in which n nodes colla...
research
∙
06/10/2021
A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip
We introduce the continuized Nesterov acceleration, a close variant of N...
research
∙
06/07/2021
Decentralized Optimization with Heterogeneous Delays: a Continuous-Time Approach
In decentralized optimization, nodes of a communication network privatel...
research
∙
11/04/2020
Asynchrony and Acceleration in Gossip Algorithms
This paper considers the minimization of a sum of smooth and strongly co...
research
∙
06/25/2020
Dual-Free Stochastic Decentralized Optimization with Variance Reduction
We consider the problem of training machine learning models on distribut...
research
∙
05/20/2020
An Optimal Algorithm for Decentralized Finite Sum Optimization
Modern large-scale finite-sum optimization relies on two key aspects: di...
research
∙
02/25/2020
Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
We consider the setting of distributed empirical risk minimization where...
research
∙
05/27/2019
An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums
Modern large-scale finite-sum optimization relies on two key aspects: di...
research
∙
02/19/2019
Who started this rumor? Quantifying the natural differential privacy guarantees of gossip protocols
Gossip protocols, also called rumor spreading or epidemic protocols, are...
research
∙
01/28/2019
Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite Sums
In this work, we study the problem of minimizing the sum of strongly con...
research
∙
10/05/2018
Accelerated Decentralized Optimization with Local Updates for Smooth and Strongly Convex Objectives
In this paper, we study the problem of minimizing a sum of smooth and st...
research
∙
04/10/2017