Publications (24)
Long-Context Linear System Identification
OÄuz Kaan Yüksel, Mathieu Even, Nicolas Flammarion
This paper addresses the problem of long-context linear system identification, where the state of a dynamical system at time depends linearly on previous states ove…
A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip
Mathieu Even, Raphaël Berthier, Francis Bach +5
We introduce the continuized Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continuou…
Privacy Auditing with Zero (0) Training Run
Tudor Cebere, Mathieu Even, Linus Bleistein +1
Privacy auditing provides empirical lower bounds on the differential privacy parameters of learning algorithms. Existing methods, however, require interventional access to the trai…
Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging
Edwige Cyffers, Mathieu Even, Aurélien Bellet +1
Decentralized optimization is increasingly popular in machine learning for its scalability and efficiency. Intuitively, it should also provide better privacy guarantees, as nodes o…
Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
Kevin Scaman, Mathieu Even, Batiste Le Bars +1
In this paper, our aim is to analyse the generalization capabilities of first-order methods for statistical learning in multiple, different yet related, scenarios including supervi…
Rethinking the Win Ratio: A Causal Framework for Hierarchical Outcome Analysis
Mathieu Even, Julie Josse
Quantifying causal effects in the presence of complex and multivariate outcomes remains a key challenge in treatment evaluation. For hierarchical multivariate outcomes, the FDA rec…
Stochastic Gradient Descent under Markovian Sampling Schemes
Mathieu Even
We study a variation of vanilla stochastic gradient descent where the optimizer only has access to a Markovian sampling scheme. These schemes encompass applications that range from…
Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction
Radu-Alexandru Dragomir, Mathieu Even, Hadrien Hendrikx
We study the problem of minimizing a relatively-smooth convex function using stochastic Bregman gradient methods. We first prove the convergence of Bregman Stochastic Gradient Desc…
Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization
Mathieu Even, Anastasia Koloskova, Laurent Massoulié
Decentralized and asynchronous communications are two popular techniques to speedup communication complexity of distributed machine learning, by respectively removing the dependenc…
Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
Mathieu Even, Luca Ganassali, Jakob Maier +1
The Procrustes-Wasserstein problem consists in matching two high-dimensional point clouds in an unsupervised setting, and has many applications in natural language processing and c…
Asynchronous speedup in decentralized optimization
Mathieu Even, Hadrien Hendrikx, Laurent Massoulie
In decentralized optimization, nodes of a communication network each possess a local objective function, and communicate using gossip-based methods in order to minimize the average…
Concentration of Non-Isotropic Random Tensors with Applications to Learning and Empirical Risk Minimization
Mathieu Even, Laurent Massoulié
Dimension is an inherent bottleneck to some modern learning tasks, where optimization methods suffer from the size of the data. In this paper, we study non-isotropic distributions…
Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays
Konstantin Mishchenko, Francis Bach, Mathieu Even +1
The existing analysis of asynchronous stochastic gradient descent (SGD) degrades dramatically when any delay is large, giving the impression that performance depends primarily on t…
Causal Evaluation of Membership Inference Attacks
Mathieu Even, Clément Berenfeld, Linus Bleistein +3
Membership Inference Attacks (MIAs) aim to distinguish training points (members) from unseen data (non-members), and are widely used to quantify memorization and assess privacy ris…
Policy learning under constraint: Maximizing a primary outcome while controlling an adverse event
Laura Fuentes-Vicente, Mathieu Even, Gaelle Dormion +2
A medical policy aims to support decision-making by mapping patient characteristics to individualized treatment recommendations. Standard approaches typically optimize a single out…
Noiseless Privacy-Preserving Decentralized Learning
Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec +4
Decentralized learning (DL) enables collaborative learning without a server and without training data leaving the users' devices. However, the models shared in DL can still be used…
Sample Optimality and All-for-all Strategies in Personalized Federated and Collaborative Learning
Mathieu Even, Laurent Massoulié, Kevin Scaman
In personalized Federated Learning, each member of a potentially large set of agents aims to train a model minimizing its loss function averaged over its local data distribution. W…
Asynchrony and Acceleration in Gossip Algorithms
Mathieu Even, Hadrien Hendrikx, Laurent Massoulié
This paper considers the minimization of a sum of smooth and strongly convex functions dispatched over the nodes of a communication network. Previous works on the subject either fo…
Meta-learning of shared linear representations beyond well-specified linear regression
Mathieu Even, Laurent Massoulié
Motivated by multi-task and meta-learning approaches, we consider the problem of learning structure shared by tasks or users, such as shared low-rank representations or clustered s…
Set-Valued Policy Learning
Laura Fuentes-Vicente, Mathieu Even, Gaëlle Dormion +3
Conventional treatment policies map patient covariates to a single recommended intervention in order to maximize expected clinical outcomes. Although a rich body of causal inferenc…
Preference-based Conditional Treatment Effects and Policy Learning
Dovid Parnas, Mathieu Even, Julie Josse +1
We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment Effect (CPTE). CP…
Model Agnostic Differentially Private Causal Inference
Christian Janos Lebeda, Mathieu Even, Aurélien Bellet +1
Estimating causal effects from observational data is essential in fields such as medicine, economics and social sciences, where privacy concerns are paramount. We propose a general…
Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
Pierre Aguié, Mathieu Even, Laurent Massoulié
We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector products are available, which can arise…
(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability
Mathieu Even, Scott Pesme, Suriya Gunasekar +1
In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over dia…