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
Flexible Parametric Inference for Space-Time Hawkes Processes 2025
Emilia Siviero, Guillaume Staerman, Stephan Clémençon, Thomas MoreauIn DSAA
Many modern spatio-temporal data sets, in sociology, epidemiology or seismology, for example, exhibit self-exciting characteristics, triggering and clustering behaviors both at the same time, that a suitable Hawkes space-time process can accurately capture. This paper aims to develop a fast and flexible parametric inference technique to recover the parameters of the kernel functions involved in the intensity function of a space-time Hawkes process based on such data. Our statistical ...
Many modern spatio-temporal data sets, in sociology, epidemiology or seismology, for example, exhibit self-exciting characteristics, triggering and clustering behaviors both at the same time, that a suitable Hawkes space-time process can accurately capture. This paper aims to develop a fast and flexible parametric inference technique to recover the parameters of the kernel functions involved in the intensity function of a space-time Hawkes process based on such data. Our statistical approach combines three key ingredients: 1) kernels with finite support are considered, 2) the space-time domain is appropriately discretized, and 3) (approximate) precomputations are used. The inference technique we propose then consists of a l2 gradient-based solver that is fast and statistically accurate. In addition to describing the algorithmic aspects, numerical experiments have been carried out on synthetic and real spatio-temporal data, providing solid empirical evidence of the relevance of the proposed methodology.
Filling the gaps: a story of priors and conditional probabilities 28 Sep 2025,
At Inverse Problem and Imaging - CIRM, Luminy
Inverse problems are often ill-posed: incomplete measurements, noise, and ambiguity mean that we must rely on priors to reconstruct meaningful solutions. In the first part of this talk, I will present recent work that analyzes the limitations and challenges of these approaches when solving unsupervised inverse problems—how the choice of priors can bias reconstructions, how conditional models interact with measurement operators, and what this reveals about the fundamental difficulty of filling...
Inverse problems are often ill-posed: incomplete measurements, noise, and ambiguity mean that we must rely on priors to reconstruct meaningful solutions. In the first part of this talk, I will present recent work that analyzes the limitations and challenges of these approaches when solving unsupervised inverse problems—how the choice of priors can bias reconstructions, how conditional models interact with measurement operators, and what this reveals about the fundamental difficulty of filling in missing information.
Building on this perspective, I will then introduce FIRE (Fixed point Restoration), a framework that addresses these challenges by defining implicit priors not just through denoisers but through general restoration models. The key idea is to characterize natural signals as fixed points of a degradation–restoration cycle, enabling a principled and flexible way to integrate pretrained networks into inverse problem solvers. This fixed-point view not only broadens the class of usable priors but also leads to robust, algorithms with strong empirical performance.
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.