26 citations · 58 across the 8 of their papers we have counts for
10 papers
Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching
Ségolène Martin, Anne Gagneux, Quentin Bertrand +2
Flow matching and diffusion can be trained to predict different quantities, most commonly the data , the source noise , or the velocity~. Although theoretically equiva…
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
Quentin Bertrand, Anne Gagneux, Mathurin Massias +1
Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand…
Beyond L1: Faster and Better Sparse Models with skglm
Quentin Bertrand, Quentin Klopfenstein, Pierre-Antoine Bannier +2
We propose a new fast algorithm to estimate any sparse generalized linear model with convex or non-convex separable penalties. Our algorithm is able to solve problems with millions…
Graph-Theoretic Models of Resource Distribution for Cyber-Physical Systems of Disaster-Affected Regions
Kenneth Johnson, Samaneh Madanian, Roopak Sinha
We propose a tool-supported framework to reason about requirements constraining resource distributions and devise strategies for routing essential services in a disaster-affected r…
Implicit differentiation for fast hyperparameter selection in non-smooth convex learning
Quentin Bertrand, Quentin Klopfenstein, Mathurin Massias +4
Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order method…
Anderson acceleration of coordinate descent
Quentin Bertrand, Mathurin Massias
Acceleration of first order methods is mainly obtained via inertial techniques à la Nesterov, or via nonlinear extrapolation. The latter has known a recent surge of interest, with…