31 citations · 88 across the 18 of their papers we have counts for
11 papers · 1 filter
Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks
Alexandre Declèves, Etienne Boursier, Nicolas Flammarion
Adapting pretrained models to downstream tasks with limited data has become a central paradigm in modern deep learning. Yet, despite its widespread practical success, how fine-tuni…
Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks
Etienne Boursier, Nicolas Flammarion
Fine-tuning pre-trained models on specialized tasks with scarce data is central to modern deep learning. Despite its empirical success, theoretical understanding of fine-tuning rem…
Penalising the biases in norm regularisation enforces sparsity
Etienne Boursier, Nicolas Flammarion
Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between regularising parameters' norm and ob…
A survey on multi-player bandits
Etienne Boursier, Vianney Perchet
Due mostly to its application to cognitive radio networks, multiplayer bandits gained a lot of interest in the last decade. A considerable progress has been made on its theoretical…
Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
Etienne Boursier, Loucas Pillaud-Vivien, Nicolas Flammarion
The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its su…
Trace norm regularization for multi-task learning with scarce data
Etienne Boursier, Mikhail Konobeev, Nicolas Flammarion
Multi-task learning leverages structural similarities between multiple tasks to learn despite very few samples. Motivated by the recent success of neural networks applied to data-s…
Decentralized Learning in Online Queuing Systems
Flore Sentenac, Etienne Boursier, Vianney Perchet
Motivated by packet routing in computer networks, online queuing systems are composed of queues receiving packets at different rates. Repeatedly, they send packets to servers, each…
Making the most of your day: online learning for optimal allocation of time
Etienne Boursier, Tristan Garrec, Vianney Perchet +1
We study online learning for optimal allocation when the resource to be allocated is time. %Examples of possible applications include job scheduling for a computing server, a drive…
Statistical Efficiency of Thompson Sampling for Combinatorial Semi-Bandits
Pierre Perrault, Etienne Boursier, Vianney Perchet +1
We investigate stochastic combinatorial multi-armed bandit with semi-bandit feedback (CMAB). In CMAB, the question of the existence of an efficient policy with an optimal asymptoti…
Utility/Privacy Trade-off through the lens of Optimal Transport
Etienne Boursier, Vianney Perchet
Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility. These two ob…
A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players
Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian +1
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved…