8 papers · 1 filter
Class Adaptive Conformal Training
Badr-Eddine Marani, Julio Silva-Rodriguez, Ismail Ben Ayed +3
Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates. As a result, they can be overconfident…
Learning Task-Agnostic Representations through Multi-Teacher Distillation
Philippe Formont, Maxime Darrin, Banafsheh Karimian +5
Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, i…
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
Antonio Emanuele CinÃ, Jérôme Rony, Maura Pintor +5
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using differen…
A Strong Baseline for Molecular Few-Shot Learning
Philippe Formont, Hugo Jeannin, Pablo Piantanida +1
Few-shot learning has recently attracted significant interest in drug discovery, with a recent, fast-growing literature mostly involving convoluted meta-learning strategies. We rev…
Variable Bregman Majorization-Minimization Algorithm and its Application to Dirichlet Maximum Likelihood Estimation
Ségolène Martin, Jean-Christophe Pesquet, Gabriele Steidl +1
We propose a novel Bregman descent algorithm for minimizing a convex function that is expressed as the sum of a differentiable part (defined over an open set) and a possibly nonsmo…
When is an Embedding Model More Promising than Another?
Maxime Darrin, Philippe Formont, Ismail Ben Ayed +2
Embedders play a central role in machine learning, projecting any object into numerical representations that can, in turn, be leveraged to perform various downstream tasks. The eva…