Publications
The papers below are classified by topics. For a chronological list, please see my Google Scholar profile.
- Bandit algorithms, global optimization and beyond
- Deep learning
- Uncertainty quantification (and beyond) for safety-critical systems
- (Non)parametric regression and classification
- Lower bounds theory
My contributions are mainly theoretical, but I am also strongly interested in how these results meet practical needs. In particular, the application-oriented papers are tagged with 
.
Bandit algorithms, global optimization and beyond
- Diversity-Preserving K-Armed Bandits, Revisited. [paper]
Hédi Hadiji, Sébastien Gerchinovitz, Jean-Michel Loubes, and Gilles Stoltz.
Transactions on Machine Learning Research, July 2024.
- Certified multi-fidelity zeroth-order optimization. [journal] [preprint]
Étienne de Montbrun and Sébastien Gerchinovitz.
SIAM/ASA Journal on Uncertainty Quantification 12(4):1135-1164, 2024.
- Adaptive approximation of monotone functions. [preprint]
Pierre Gaillard, Sébastien Gerchinovitz, and Étienne de Montbrun.
arXiv:2309.07530, 2023.
- Regret analysis of the Piyavskii-Shubert algorithm for global Lipschitz optimization. [preprint]
Clément Bouttier, Tommaso R. Cesari, Mélanie Ducoffe, and Sébastien Gerchinovitz.
arXiv:2002.02390, 2022.
- Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates. [proceedings]
François Bachoc, Tommaso R. Cesari, and Sébastien Gerchinovitz.
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 24180-24192, 2021.
- The sample complexity of level set approximation. [proceedings]
François Bachoc, Tommaso R. Cesari, and Sébastien Gerchinovitz.
Proceedings of the Twenty Fourth International Conference on Artificial Intelligence and Statistics (AISTATS 2021, oral presentation), PMLR 130:424-432, 2021.
- Optimization of a SSP's Header Bidding Strategy using Thompson Sampling. [pdf] [video]
Grégoire Jauvion, Nicolas Grislain, Pascal Dkengne Sielenou, Aurélien Garivier, and Sébastien Gerchinovitz.
Proceedings of KDD 2018, Applied Data Science track, 2018.
- Refined lower bounds for adversarial bandits. [proceedings] [preprint]
Sébastien Gerchinovitz and Tor Lattimore.
Advances in Neural Information Processing Systems 29 (NIPS 2016), 2016.
- A multiple-play bandit algorithm applied to recommender systems. [proceedings]
Jonathan Louëdec, Max Chevalier, Josiane Mothe, Aurélien Garivier, and Sébastien Gerchinovitz.
Proceedings of the 28th International Florida Artificial Intelligence Research Society Conference (FLAIRS 2015), 67-72, 2015.
- Adaptive simulated annealing with homogenization for aircraft trajectory optimization. [proceedings]
Clément Bouttier, Olivier Babando, Sébastien Gadat, Sébastien Gerchinovitz, Serge Laporte, and Florence Nicol.
Operations Research Proceedings 2015, 569-574, 2017.
Deep learning
- The loss landscape of deep linear neural networks: a second-order analysis. [journal]
El Mehdi Achour, François Malgouyres, and Sébastien Gerchinovitz.
Journal of Machine Learning Research 25(242):1-76, 2024.
- A general approximation lower bound in L^p norm, with applications to feed-forward neural networks. [proceedings] [full paper]
El Mehdi Achour, Armand Foucault, Sébastien Gerchinovitz, and François Malgouyres.
Proceedings of NeurIPS 2022.
- Numerical influence of ReLU'(0) on backpropagation. [paper with erratum]
David Bertoin, Jérôme Bolte, Sébastien Gerchinovitz, and Edouard Pauwels.
Advances in Neural Information Processing Systems 34 (NeurIPS 2021), 468-479, 2021.
Uncertainty quantification (and beyond) for safety-critical systems
- On the feasibility of EASA learning assurance objectives for machine learning components [paper]
Florence de Grancey, Sébastien Gerchinovitz, Lucian Alecu, Hugues Bonnin, Joseba Dalmau, Kevin Delmas, and Franck Mamalet.
Proceedings of ERTS 2024 (best paper award).
- Object detection with probabilistic guarantees: a conformal prediction approach [preprint]
Florence de Grancey, Jean-Luc Adam, Lucian Alecu, Sébastien Gerchinovitz, Franck Mamalet, and David Vigouroux.
Proceedings of WAISE 2022 (best paper award).
- Can we reconcile safety objectives with machine learning performances? [proceedings]
Hugues Bonnin, Eric Jenn, Lucian Alecu, Thomas Fel, Laurent Gardes, Sébastien Gerchinovitz, Ludovic Ponsolle, Franck Mamalet, Vincent Mussot, Cyril Cappi, Kévin Delmas and Baptiste Lefevre.
Proceedings of ERTS 2022 (best paper award).
- A High-Probability Safety Guarantee for Shifted Neural Network Surrogates. [pdf] [video]
Mélanie Ducoffe, Sébastien Gerchinovitz, and Jayant Sen Gupta.
Proceedings of the Workshop on Artificial Intelligence Safety (SafeAI 2020), 74-82, 2020.
(Non)parametric regression and classification
- Optimal functional supervised classification with separation condition. [journal] [preprint, with supplement]
Sébastien Gadat, Sébastien Gerchinovitz, and Clément Marteau.
Bernoulli 26(3), 1797-1831, 2020.
- Uniform regret bounds over R^d for the sequential linear regression problem with the square loss. [proceedings]
Pierre Gaillard, Sébastien Gerchinovitz, Malo Huard, and Gilles Stoltz.
Proceedings of the 30th international conference on Algorithmic Learning Theory (ALT 2019), PMLR 98:404-432, 2019.
- Algorithmic chaining and the role of partial feedback in online nonparametric learning.
Nicolò Cesa-Bianchi, Pierre Gaillard, Claudio Gentile, and Sébastien Gerchinovitz. [long] [short]
Proceedings of the 2017 Conference on Learning Theory (COLT 2017), PMLR 65:465-481, 2017.
- A chaining algorithm for online nonparametric regression. [proceedings] [video]
Pierre Gaillard and Sébastien Gerchinovitz.
Proceedings of the 28th Conference on Learning Theory (COLT 2015), PMLR 40:764-796, 2015.
- Adaptive and optimal online linear regression on L1-balls. [journal] [preprint]
Sébastien Gerchinovitz and Jia Yuan Yu.
Theoretical Computer Science 519:4-28, 2014.
NB : A shorter version appeared in the proceedings of ALT 2011. - Sparsity regret bounds for individual sequences in online linear regression. [journal]
Sébastien Gerchinovitz.
Journal of Machine Learning Research 14(22):729-769, 2013.
NB : A shorter version appeared in the proceedings of COLT 2011. Here is a video of the talk.
Lower bounds theory
- Fano's inequality for random variables. [journal] [preprint]
Sébastien Gerchinovitz, Pierre Ménard, and Gilles Stoltz.
Statistical Science 35(2), 178-201, 2020.
- A general approximation lower bound in L^p norm, with applications to feed-forward neural networks (2022)
- Instance-Dependent Bounds for Zeroth-order Lipschitz Optimization with Error Certificates (2021)
- The sample complexity of level set approximation (2021)
- Optimal functional supervised classification with separation condition (2020)
- Uniform regret bounds over R^d for the sequential linear regression problem with the square loss (2019)
- Refined lower bounds for adversarial bandits (2016)
PhD thesis
- Prediction of individual sequences and prediction in the statistical framework:
some links around sparse regression and aggregation techniques. [pdf] [slides]
Sébastien Gerchinovitz.
PhD thesis, Université Paris-Sud 11, 2011.
Technical reports
-
A further look at sequential aggregation rules for ozone ensemble forecasting. [pdf]
Sébastien Gerchinovitz, Vivien Mallet, and Gilles Stoltz.
Technical report (research internship at ENS Paris / INRIA Paris-Rocquencourt), 2008.