no code implementations • 30 May 2024 • Siavash Golkar, Alberto Bietti, Mariel Pettee, Michael Eickenberg, Miles Cranmer, Keiya Hirashima, Geraud Krawezik, Nicholas Lourie, Michael McCabe, Rudy Morel, Ruben Ohana, Liam Holden Parker, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Shirley Ho

Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications.

1 code implementation • 29 Feb 2024 • David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard

Assuming arbitrary parametric Gaussian noise, we develop a Gibbs algorithm that alternates sampling steps from a conditional diffusion model trained to map the signal prior to the family of noise distributions, and a Monte Carlo sampler to infer the noise parameters.

no code implementations • 25 Oct 2023 • David Heurtel-Depeiges, Blakesley Burkhart, Ruben Ohana, Bruno Régaldo-Saint Blancard

We investigate diffusion-based modeling of the dust foreground and its interest for component separation.

2 code implementations • 4 Oct 2023 • Siavash Golkar, Mariel Pettee, Michael Eickenberg, Alberto Bietti, Miles Cranmer, Geraud Krawezik, Francois Lanusse, Michael McCabe, Ruben Ohana, Liam Parker, Bruno Régaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

Large Language Models have not yet been broadly adapted for the analysis of scientific datasets due in part to the unique difficulties of tokenizing numbers.

1 code implementation • 4 Oct 2023 • Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles Cranmer, Alberto Bietti, Michael Eickenberg, Siavash Golkar, Geraud Krawezik, Francois Lanusse, Mariel Pettee, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling.

1 code implementation • 4 Oct 2023 • Liam Parker, Francois Lanusse, Siavash Golkar, Leopoldo Sarra, Miles Cranmer, Alberto Bietti, Michael Eickenberg, Geraud Krawezik, Michael McCabe, Ruben Ohana, Mariel Pettee, Bruno Regaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

These embeddings can then be used - without any model fine-tuning - for a variety of downstream tasks including (1) accurate in-modality and cross-modality semantic similarity search, (2) photometric redshift estimation, (3) galaxy property estimation from both images and spectra, and (4) morphology classification.

1 code implementation • 12 May 2023 • Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower

MoMo uses momentum estimates of the losses and gradients sampled at each iteration to build a model of the loss function.

1 code implementation • 7 Jun 2022 • Ruben Ohana, Kimia Nadjahi, Alain Rakotomamonjy, Liva Ralaivola

The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance.

1 code implementation • 4 Feb 2022 • Jonas Wacker, Ruben Ohana, Maurizio Filippone

Commonly used approaches avoid computing the high-dimensional tensor product explicitly, resulting in a suboptimal dependence of $\mathcal{O}(3^p)$ in the embedding dimension.

no code implementations • ICML Workshop AML 2021 • Alessandro Cappelli, Julien Launay, Laurent Meunier, Ruben Ohana, Iacopo Poli

Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent.

no code implementations • NeurIPS 2021 • Ruben Ohana, Hamlet J. Medina Ruiz, Julien Launay, Alessandro Cappelli, Iacopo Poli, Liva Ralaivola, Alain Rakotomamonjy

Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direct Feedback Alignment (DFA), an effective alternative to backpropagation.

no code implementations • 29 Apr 2021 • Daniel Hesslow, Alessandro Cappelli, Igor Carron, Laurent Daudet, Raphaël Lafargue, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli

Randomized Numerical Linear Algebra (RandNLA) is a powerful class of methods, widely used in High Performance Computing (HPC).

1 code implementation • 6 Jan 2021 • Alessandro Cappelli, Ruben Ohana, Julien Launay, Laurent Meunier, Iacopo Poli, Florent Krzakala

In the white-box setting, our defense works by obfuscating the parameters of the random projection.

1 code implementation • 24 Nov 2020 • Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana, Sebastian Goldt

Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to the ubiquitous backpropagation algorithm for training deep neural networks.

1 code implementation • NeurIPS 2020 • Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala

Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained.

1 code implementation • 22 Oct 2019 • Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet

Approximating kernel functions with random features (RFs)has been a successful application of random projections for nonparametric estimation.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.