no code implementations • 28 Feb 2024 • Vivien Cabannes, Berfin Simsek, Alberto Bietti
This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings.
no code implementations • 20 Feb 2024 • Charles Arnal, Vivien Cabannes, Vianney Perchet
The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments.
no code implementations • 23 Nov 2023 • Vivien Cabannes, Charles Arnal
The number of sampling methods could be daunting for a practitioner looking to cast powerful machine learning methods to their specific problem.
no code implementations • 4 Oct 2023 • Vivien Cabannes, Elvis Dohmatob, Alberto Bietti
Learning arguably involves the discovery and memorization of abstract rules.
no code implementations • 20 Jun 2023 • Vivien Cabannes, Carles Domingo-Enrich
The theory of statistical learning has focused on variational objectives expressed on functions.
Out-of-Distribution Generalization Weakly-supervised Learning
1 code implementation • 1 Jun 2023 • Vivien Cabannes, Francis Bach
Historically, the machine learning community has derived spectral decompositions from graph-based approaches.
1 code implementation • ICCV 2023 • Vivien Cabannes, Leon Bottou, Yann Lecun, Randall Balestriero
Third, it provides a proper active learning framework yielding low-cost solutions to annotate datasets, arguably bringing the gap between theory and practice of active learning that is based on simple-to-answer-by-non-experts queries of semantic relationships between inputs.
no code implementations • 6 Feb 2023 • Vivien Cabannes, Bobak T. Kiani, Randall Balestriero, Yann Lecun, Alberto Bietti
Self-supervised learning (SSL) has emerged as a powerful framework to learn representations from raw data without supervision.
no code implementations • 7 Nov 2022 • Vivien Cabannes, Alberto Bietti, Randall Balestriero
Unsupervised representation learning aims at describing raw data efficiently to solve various downstream tasks.
no code implementations • 23 Sep 2022 • Vivien Cabannes
This thesis is motivated by the following question: can we derive a more generic framework than the one of supervised learning in order to learn from clutter data?
1 code implementation • 26 May 2022 • Vivien Cabannes, Francis Bach, Vianney Perchet, Alessandro Rudi
The workhorse of machine learning is stochastic gradient descent.
no code implementations • 20 May 2022 • Vivien Cabannes, Stefano Vigogna
Classification is often the first problem described in introductory machine learning classes.
1 code implementation • 4 Feb 2021 • Vivien Cabannes, Francis Bach, Alessandro Rudi
Machine learning approached through supervised learning requires expensive annotation of data.
no code implementations • 1 Feb 2021 • 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.
no code implementations • 12 Oct 2020 • Vivien Cabannes, Thomas Kerdreux, Louis Thiry
We propose visual creations that put differences in algorithms and humans \emph{perceptions} into perspective.
2 code implementations • NeurIPS 2021 • Vivien Cabannes, Loucas Pillaud-Vivien, Francis Bach, Alessandro Rudi
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.
2 code implementations • ICML 2020 • Vivien Cabannes, Alessandro Rudi, Francis Bach
Annotating datasets is one of the main costs in nowadays supervised learning.
no code implementations • 10 Oct 2019 • Vivien Cabannes, Thomas Kerdreux, Louis Thiry, Tina Campana, Charly Ferrandes
We propose a new form of human-machine interaction.