I am a researcher in the parietal team @ INRIA Saclay, since autumn 2019, working on unsupervised learning for time series and on deep learning methods applied to solving inverse problems.
My research interests touch several areas of Machine Learning, Signal Processing and High-Dimensional Statistics. In particular, I have been working on Convolutional Dictionary Learning, studying both their computational aspects and their possible application to pattern analysis. I am also interested in theoretical properties of learned optimization algorithms such as LISTA, in particular for the resolution of inverse problems.
I did my PhD under the supervision of Nicolas Vayatis and Laurent Oudre, in the CMLA @ ENS Paris-Saclay. My PhD focuses on convolutional representations and their applications to physiological signals. I continued working on unsupervised learning for time series with application to electrophysiological recordings during a 1,5 year in the Parietal Team. I am also involved in open-source projects such as joblib or loky, for parallel scientific computing, and benchopt, for reproducible benchmarks in optimization.
Latest publication and projects
A lower bound and a near-optimal algorithm for bilevel empirical risk minimization Mathieu Dagréou, Thomas Moreau, Samuel Vaiter, Pierre Ablin,May 2024,In proceedings of AISTATS
Bilevel optimization problems, which are problems where two optimization problems are nested, have more and more applications in machine learning. In many practical cases, the upper and the lower objectives correspond to empirical risk minimization problems and therefore have a sum structure. In this context, we propose a bilevel extension of the celebrated SARAH algorithm. We demonstrate that the algorithm requires O((n+m)^{1/2}ε^{−1}) gradient computations to achieve ε-stationarity ...
Bilevel optimization problems, which are problems where two optimization problems are nested, have more and more applications in machine learning. In many practical cases, the upper and the lower objectives correspond to empirical risk minimization problems and therefore have a sum structure. In this context, we propose a bilevel extension of the celebrated SARAH algorithm. We demonstrate that the algorithm requires O((n+m)^{1/2}ε^{−1}) gradient computations to achieve ε-stationarity with n+m the total number of samples, which improves over all previous bilevel algorithms. Moreover, we provide a lower bound on the number of oracle calls required to get an approximate stationary point of the objective function of the bilevel problem. This lower bound is attained by our algorithm, which is therefore optimal in terms of sample complexity.
A journey through unrolling for inverse problems 10 Apr 2024,At CIMS - Imaging inverse problems and generating models -- Edinburgh
Inverse problems are ubiquitous in observational science such as imaging, neurosciences or astrophysics. They consist in recovering a signal given noisy observations through a measurement operator. To solve such problems, Machine learning approaches have been proposed based on algorithm unrolling. With such techniques, classical optimization algorithms used to solve inverse problems can be seen as differentiable procedures with parameters that can be learned. In this talk, I will ...
Inverse problems are ubiquitous in observational science such as imaging, neurosciences or astrophysics. They consist in recovering a signal given noisy observations through a measurement operator. To solve such problems, Machine learning approaches have been proposed based on algorithm unrolling. With such techniques, classical optimization algorithms used to solve inverse problems can be seen as differentiable procedures with parameters that can be learned.
In this talk, I will present results that aim at understanding what unrolled algorithms learn and their link to the original associated bilevel problem. Based on results from [Ablin et al 2019], I show that in the smooth case, the gradient of the unrolled problem aligns with the ones of the original problem. Then, I will present contributions from [Malézieux et al. 2022] that show that in the non-smooth case, the jacobian estimation is unstable and too many iterations can be harmful.
Finally, I will present recent results from [Ramzi et al. 2023] showing that when unrolled networks are learned with fixed number of iteration, it is not beneficial to use more iteration at test time.
Loky Apr 2023
The aim of this project is to provide a robust, cross-platform and cross-version implementation of the ProcessPoolExecutor class of concurrent.futures.
The aim of this project is to provide a robust, cross-platform and cross-version implementation of the ProcessPoolExecutor class of concurrent.futures. It features:
Deadlock free implementation: one of the major concern in standard multiprocessing and concurrent.futures libraries is the ability of the Pool/Executor to handle crashes of worker processes. This library intends to fix those possible deadlocks and send back meaningful errors.
Consistent spawn behavior: All processes are started using fork/exec on POSIX systems. This ensures safer interactions with third party libraries.
Reusable executor: strategy to avoid respawning a complete executor every time. A singleton pool can be reused (and dynamically resized if necessary) across consecutive calls to limit spawning and shutdown overhead. The worker processes can be shutdown automatically after a configurable idling timeout to free system resources.