9 citations · 39 across the 17 of their papers we have counts for
17 papers
Learning with Hidden Factorial Structure
Charles Arnal, Clement Berenfeld, Simon Rosenberg +1
Statistical learning in high-dimensional spaces is challenging without a strong underlying data structure. Recent advances with foundational models suggest that text and image data…
-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
Vlad Sobal, Mark Ibrahim, Randall Balestriero +5
Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from se…
Birth of a Transformer: A Memory Viewpoint
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt +2
Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their i…
The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
Vivien Cabannes, Francis Bach
Historically, the machine learning community has derived spectral decompositions from graph-based approaches. We break with this approach and prove the statistical and computationa…
How many samples are needed to leverage smoothness?
Vivien Cabannes, Stefano Vigogna
A core principle in statistical learning is that smoothness of target functions allows to break the curse of dimensionality. However, learning a smooth function seems to require en…
Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need
Vivien Cabannes, Leon Bottou, Yann Lecun +1
Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are know…
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
Vivien Cabannes, Bobak T. Kiani, Randall Balestriero +2
Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision. Yet in practice, engineers face issues such as instab…
On minimal variations for unsupervised representation learning
Vivien Cabannes, Alberto Bietti, Randall Balestriero
Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks. It has been approached with many techniques, such as manifold learni…
From Weakly Supervised Learning to Active Learning
Vivien Cabannes
Applied mathematics and machine computations have raised a lot of hope since the recent success of supervised learning. Many practitioners in industries have been trying to switch…
Active Labeling: Streaming Stochastic Gradients
Vivien Cabannes, Francis Bach, Vianney Perchet +1
The workhorse of machine learning is stochastic gradient descent. To access stochastic gradients, it is common to consider iteratively input/output pairs of a training dataset. Int…
A Case of Exponential Convergence Rates for SVM
Vivien Cabannes, Stefano Vigogna
Classification is often the first problem described in introductory machine learning classes. Generalization guarantees of classification have historically been offered by Vapnik-C…
Disambiguation of weak supervision with exponential convergence rates
Vivien Cabannes, Francis Bach, Alessandro Rudi
Machine learning approached through supervised learning requires expensive annotation of data. This motivates weakly supervised learning, where data are annotated with incomplete y…
Fast rates in structured prediction
Vivien Cabannes, Alessandro Rudi, Francis Bach
Discrete supervised learning problems such as classification are often tackled by introducing a continuous surrogate problem akin to regression. Bounding the original error, betwee…
Diptychs of human and machine perceptions
Vivien Cabannes, Thomas Kerdreux, Louis Thiry
We propose visual creations that put differences in algorithms and humans \emph{perceptions} into perspective. We exploit saliency maps of neural networks and visual focus of human…
Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning
Vivien Cabannes, Loucas Pillaud-Vivien, Francis Bach +1
As annotations of data can be scarce in large-scale practical problems, leveraging unlabelled examples is one of the most important aspects of machine learning. This is the aim of…
Structured Prediction with Partial Labelling through the Infimum Loss
Vivien Cabannes, Alessandro Rudi, Francis Bach
Annotating datasets is one of the main costs in nowadays supervised learning. The goal of weak supervision is to enable models to learn using only forms of labelling which are chea…
Dialog on a canvas with a machine
Vivien Cabannes, Thomas Kerdreux, Louis Thiry +2
We propose a new form of human-machine interaction. It is a pictorial game consisting of interactive rounds of creation between artists and a machine. They repetitively paint one a…