Publications



65 documents

Journal articles

  • Warren Hare, Gabriel Jarry-Bolduc, Sébastien Kerleau, Clément Royer. Using orthogonally structured positive bases for constructing positive k-spanning sets with cosine measure guarantees. Linear Algebra and its Applications, 2024, 680, pp.183-207. ⟨10.1016/j.laa.2023.10.006⟩. ⟨hal-04334281⟩
  • Lindon Roberts, Clément Royer. Direct Search Based on Probabilistic Descent in Reduced Spaces. SIAM Journal on Optimization, 2023, 33 (4), pp.3057-3082. ⟨10.1137/22M1488569⟩. ⟨hal-04334275⟩
  • Madalina Olteanu, Fabrice Rossi, Florian Yger. Meta-survey on outlier and anomaly detection. Neurocomputing, 2023, 555, pp.126634. ⟨10.1016/j.neucom.2023.126634⟩. ⟨hal-04335748⟩
  • Warren Hare, Clément Royer. Detecting negative eigenvalues of exact and approximate Hessian matrices in optimization. Optimization Letters, 2023, 17, pp.1739-1756. ⟨10.1007/s11590-023-02033-5⟩. ⟨hal-04334269⟩
  • Rémi Chan--Renous-Legoubin, Clément Royer. A nonlinear conjugate gradient method with complexity guarantees and its application to nonconvex regression. EURO Journal on Computational Optimization, 2022, 10, pp.100044. ⟨10.1016/j.ejco.2022.100044⟩. ⟨hal-03866347⟩
  • Rafael Pinot, Laurent Meunier, Florian Yger, Cédric Gouy-Pailler, Yann Chevaleyre, et al.. On the robustness of randomized classifiers to adversarial examples. Machine Learning, 2022, 111 (9), pp.3425-3457. ⟨10.1007/s10994-022-06216-6⟩. ⟨hal-03916842⟩
  • El Houcine Bergou, Youssef Diouane, Vladimir Kunc, Vyacheslav Kungurtsev, Clément Royer. A Subsampling Line-Search Method with Second-Order Results. INFORMS Journal on Optimization, 2022, 4 (4), pp.403-425. ⟨10.1287/ijoo.2022.0072⟩. ⟨hal-03946165⟩
  • El Houcine Bergou, Youssef Diouane, Vyacheslav Kungurtsev, Clément Royer. A Stochastic Levenberg--Marquardt Method Using Random Models with Complexity Results. SIAM/ASA Journal on Uncertainty Quantification, 2022, 10 (1), pp.507-536. ⟨10.1137/20M1366253⟩. ⟨hal-03866363⟩
  • Frank Curtis, Daniel Robinson, Clément Royer, Stephen Wright. Trust-Region Newton-CG with Strong Second-Order Complexity Guarantees for Nonconvex Optimization. SIAM Journal on Optimization, 2021, 31 (1), pp.518-544. ⟨10.1137/19M130563X⟩. ⟨hal-03135526⟩
  • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif. Training compact deep learning models for video classification using circulant matrices. European Conference on Computer Vision, 2018, pp.271-286. ⟨10.1007/978-3-030-11018-5_25⟩. ⟨hal-02010093⟩
  • Eric Benhamou, Beatrice Guez. Incremental Sharpe and other performance ratios. Journal of Statistical and Econometric Methods, 2018, xx, pp.2241 - 0376. ⟨hal-02012443v2⟩
  • Fabien Labernia, Florian Yger, Brice Mayag, Jamal Atif. Query-based learning of acyclic conditional preference networks from noisy data. EURO journal on decision processes, 2018, 6 (1-2), ⟨10.1007/s40070-017-0070-3⟩. ⟨hal-02074081⟩
  • Adrian Lecoutre, Benjamin Negrevergne, Florian Yger. Recognizing Art Style Automatically with deep learning. Proceedings of Machine Learning Research, 2017, 77, pp.327 - 342. ⟨hal-02004781⟩
  • Eric Benhamou. T-statistic for Autoregressive process. Journal of Statistical and Econometric Methods, 2011, 1, pp.2241 - 0376. ⟨hal-02012459⟩
  • Eric Benhamou. Gram Charlier and Edgeworth expansion for sample variance. Theoretical Mathematics and Applications, 2011, x (4), pp.1792 - 6939. ⟨hal-02012464⟩

Conference papers

  • Lucas Gnecco Heredia, Yann Chevaleyre, Benjamin Negrevergne, Laurent Meunier, Muni Sreenivas Pydi. On the Role of Randomization in Adversarially Robust Classification. Thirty-seventh Conference on Neural Information Processing Systems, NeurIPS 2023, Dec 2023, New Orleans (LA), United States. ⟨hal-04312028⟩
  • Alexandre Vérine, Benjamin Negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre. Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows. Advances in Neural Information Processing Systems, Dec 2023, Nouvelle Orléans (LA), United States. ⟨hal-04480496⟩
  • Mathieu Seraphim, Paul Dequidt, Alexis Lechervy, Florian Yger, Luc Brun, et al.. Temporal Sequences of EEG Covariance Matrices for Automated Sleep Stage Scoring with Attention Mechanisms. Computer Analysis of Images and Patterns, Sep 2023, Limassol, Cyprus. pp.67-76, ⟨10.1007/978-3-031-44240-7_7⟩. ⟨hal-04216925⟩
  • Ikko Yamane, Yann Chevaleyre, Takashi Ishida, Florian Yger. Mediated Uncoupled Learning and Validation with Bregman Divergences: Loss Family with Maximal Generality. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2023, Valencia, Spain. ⟨hal-04218995⟩
  • Marie-Constance Corsi, Sylvain Chevallier, Fabrizio de Vico Fallani, Florian Yger. Ensemble of Riemannian Classifiers for Multimodal Data: FUCONE Approach for M/EEG Data. ISBI 2023 - IEEE International Symposium on Biomedical Imaging, Apr 2023, Cartagena de Indias, Colombia. ⟨hal-04140126⟩
  • Alexandre Vérine, Benjamin Negrevergne, Fabrice Rossi, Yann Chevaleyre. On the expressivity of bi-Lipschitz normalizing flows. ACML 2022 - 14th Asian Conference on Machine Learning,, Dec 2022, Hyderabad, India. ⟨hal-03906979⟩
  • Laurent Meunier, Raphael Ettedgui, Rafaël Pinot, Yann Chevaleyre, Jamal Atif. Towards Consistency in Adversarial Classification. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Nov 2022, Virtual conference, United States. ⟨hal-04014745⟩
  • David Saltiel, Eric Benhamou. Trade Selection with Supervised Learning and OCA. ECML PKDD MIDAS 2021, Sep 2021, Bilbao (online), Spain. ⟨10.1007/978-3-030-66981-2\_1⟩. ⟨hal-02012476⟩
  • Laurent Meunier, Meyer Scetbon, Rafaël Pinot, Jamal Atif, Yann Chevaleyre. Mixed Nash Equilibria in the Adversarial Examples Game. International Conference on Machine Learning (ICML), Aug 2021, paris, France. ⟨hal-03916826⟩
  • Laurent Meunier, Iskander Legheraba, Yann Chevaleyre, Olivier Teytaud. Asymptotic convergence rates for averaging strategies. FOGA '21: Foundations of Genetic Algorithms XVI, Jul 2021, Virtual Event Austria, France. pp.1-11, ⟨10.1145/3450218.3477302⟩. ⟨hal-03916845⟩
  • Linlin Jia, Benoit Gaüzère, Florian Yger, Paul Honeine. A Metric Learning Approach to Graph Edit Costs for Regression. Proceedings of IAPR Joint International Workshops on Statistical techniques in Pattern Recognition (SPR 2020) and Structural and Syntactic Pattern Recognition (SSPR 2020), Jan 2021, Venise, Italy. ⟨10.1007/978-3-030-73973-7_23⟩. ⟨hal-03128664⟩
  • Eric Benhamou, David Saltiel, Jean-Jacques Ohana, Jamal Atif. Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning. ICPR 2020 - 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan, France. pp.10050-10057, ⟨10.1109/ICPR48806.2021.9412958⟩. ⟨hal-03815026⟩
  • Florian Yger, Sylvain Chevallier, Quentin Barthélemy, Suvrit Sra. Geodesically-convex optimization for averaging partially observed covariance matrices. Asian Conference on Machine Learning (ACML), Nov 2020, Bangkok, Thailand. pp.417 - 432. ⟨hal-02984423⟩
  • Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay. Time your hedge with Deep Reinforcement Learning. ICAPS Workshop on Planning for Financial Services (FinPlan 2020), Oct 2020, Online, France. ⟨hal-02977533⟩
  • Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay. Bridging the gap between Markowitz planning and deep reinforcement learning. ICAPS PRL, 30th International Conference on Automated Planning and Scheduling - ICAPS PRL 2020, Oct 2020, Nancy (Online), France. ⟨hal-02977530⟩
  • Jing Zhang, Caroline Petitjean, Florian Yger, Samia Ainouz. Explainability for regression CNN in fetal head circumference estimation from ultrasound images. Workshop on Interpretability of Machine Intelligence in Medical Image Computing at MICCAI 2020, Oct 2020, Lima, Peru. pp.73-82, ⟨10.1007/978-3-030-61166-8_8⟩. ⟨hal-02960164⟩
  • Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Negrevergne. Advocating for Multiple Defense Strategies against Adversarial Examples. Workshop on Machine Learning for CyberSecurity (MLCS@ECML-PKDD), Sep 2020, Ghent, Belgium. ⟨hal-03118649⟩
  • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif. Understanding and Training Deep Diagonal Circulant Neural Networks. 24th European Conference on Artificial Intelligence (ECAI), Jul 2020, Santiago, Spain. ⟨hal-03916848⟩
  • Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, Jamal Atif. Randomization matters How to defend against strong adversarial attacks. Thirty-seventh International Conference on Machine Learning, Jul 2020, Vienna, Austria. ⟨hal-02892161⟩
  • Nicolas Boria, Benjamin Negrevergne, Florian Yger. Fréchet Mean Computation in Graph Space through Projected Block Gradient Descent. ESANN 2020, 2020, Bruges, France. ⟨hal-02895832⟩
  • M. Riva, F. Yger, P. Gori, R. Cesar, Isabelle Bloch. Template-Based Graph Clustering. ECML-PKDD, Workshop on Graph Embedding and Mining (GEM), 2020, Ghent, Belgium. ⟨hal-02916167⟩
  • Matthieu Clertant, Nataliya Sokolovska, Yann Chevaleyre, Blaise Hanczar. Interpretable Cascade Classifiers with Abstention. 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Apr 2019, Naha, Japan. ⟨hal-02006252⟩
  • Ikko Yamane, Florian Yger, Jamal Atif, Masashi Sugiyama. Uplift Modeling from Separate Labels. NeurIPS, Dec 2018, Montréal, Canada. ⟨hal-02010052⟩
  • Rafael Pinot, Anne Morvan, Florian Yger, Cedric Gouy-Pailler, Jamal Atif. Graph-based Clustering under Differential Privacy. Uncertainty in Artificial Intelligence (UAI 2018), Aug 2018, Monterley, California, United States. pp.132. ⟨hal-02010071⟩
  • Anne Morvan, Krzysztof Choromanski, Cedric Gouy-Pailler, Jamal Atif. Graph sketching-based Space-efficient Data Clustering. 2018 SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics, May 2018, San Diego, United States. ⟨10.1137/1.9781611975321.2⟩. ⟨cea-01838501⟩
  • Nataliya Sokolovska, Yann Chevaleyre, Jean-Daniel Zucker. A Provable Algorithm for Learning Interpretable Scoring Systems. Twenty-First International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2018, lanzarote, Spain. ⟨hal-03916854⟩
  • Fabien Labernia, Bruno Zanuttini, Brice Mayag, Florian Yger, Jamal Atif. Online learning of acyclic conditional preference networks from noisy data. 17th IEEE International Conference on Data Mining (ICDM 2017), Nov 2017, New Orleans, United States. ⟨hal-01619969⟩
  • Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, et al.. Structured adaptive and random spinners for fast machine learning computations. 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), Apr 2017, Fort Lauderdale, Florida, United States. pp.1020-1029. ⟨hal-02010086⟩
  • Fabien Labernia, Bruno Zanuttini, Brice Mayag, Florian Yger, Jamal Atif. Online learning of acyclic conditional preference networks from noisy data. ICDM 2017, 2017, New Orleans, États-Unis. ⟨10.1109/ICDM.2017.34⟩. ⟨hal-02074110⟩
  • Quentin Brabant, Miguel Couceiro, Fabien Labernia, Amedeo Napoli. A dimensionality Reduction Approach for Qualitative Preference Aggregation. International Symposium on Aggregation and Structures (ISAS 2016), Jul 2016, Luxembourg, Luxembourg. ⟨hal-02074061⟩

Book sections

  • Laurent Meunier, Yann Chevaleyre, Jeremy Rapin, Clément Royer, Olivier Teytaud. On Averaging the Best Samples in Evolutionary Computation. Parallel Problem Solving from Nature – PPSN XVI. PPSN 2020, pp.661-674, 2020, ⟨10.1007/978-3-030-58115-2_46⟩. ⟨hal-03135540⟩

Preprints, Working Papers

  • Florentin Goyens, Clément W. Royer. Riemannian trust-region methods for strict saddle functions with complexity guarantees. 2024. ⟨hal-04397931v2⟩
  • J J Ohana, S Ohana, Eric Benhamou, D Saltiel, B Guez. Shapley values for LightGBM model applied to regime detection. 2021. ⟨hal-03320300⟩
  • Eric Benhamou, Jean Jacques Ohana, David Saltiel, Beatrice Guez. Detecting crisis event with Gradient Boosting Decision Trees. 2021. ⟨hal-03320297⟩
  • Eric Benhamou, Jean Jacques Ohana, David Saltiel, Beatrice Guez. Regime change detection with GBDT and Shapley values. 2021. ⟨hal-03320304⟩
  • Eric Benhamou. Distribution and statistics of the Sharpe Ratio. 2021. ⟨hal-03207169⟩
  • Eric Benhamou, Beatrice Guez. Computation of the marginal contribution of Sharpe ratio and other performance ratios. 2021. ⟨hal-03189299v2⟩
  • Jean Jacques Ohana, Eric Benhamou, David Saltiel, Beatrice Guez. Is the Covid equity bubble rational? A machine learning answer. 2021. ⟨hal-03189799⟩
  • Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay, Jamal Atif. AAMDRL: Augmented Asset Management with Deep Reinforcement Learning. 2020. ⟨hal-02977535⟩
  • Eric Benhamou, David Saltiel, Rida Laraki, Jamal Atif. BCMA-ES: a conjugate prior Bayesian optimization view. 2020. ⟨hal-02977523⟩
  • Alexandre Araujo, Laurent Meunier, Rafael Pinot, Benjamin Negrevergne. Robust Neural Networks using Randomized Adversarial Training. 2020. ⟨hal-02380184v2⟩
  • Eric Benhamou. A few properties of sample variance. 2019. ⟨hal-02012458⟩
  • Eric Benhamou, Jamal Atif, Rida Laraki. A discrete version of CMA-ES. 2019. ⟨hal-02011531v2⟩
  • Eric Benhamou. Kalman filter demystified: from intuition to probabilistic graphical model to real case in financial markets. 2019. ⟨hal-02012471⟩
  • David Saltiel, Eric Benhamou. Feature selection with optimal coordinate ascent (OCA). 2019. ⟨hal-02012473⟩
  • Eric Benhamou. Connecting Sharpe ratio and Student t-statistic, and beyond. 2019. ⟨hal-02012448⟩
  • Eric Benhamou, Valentin Melot. Seven proofs of the Pearson Chi-squared independence test and its graphical interpretation. 2019. ⟨hal-02012452⟩
  • Eric Benhamou, Jamal Atif, Rida Laraki. A new approach to learning in Dynamic Bayesian Networks (DBNs). 2019. ⟨hal-02011529v2⟩

Reports

  • Marie-Constance Corsi, Florian Yger, Sylvain Chevallier, Camille Noûs. Clinical BCI Challenge-WCCI2020: RIGOLETTO -- RIemannian GeOmetry LEarning, applicaTion To cOnnectivity. [Technical Report] ARAMIS, LAMSADE, LISV. 2021. ⟨hal-03139990⟩

Theses

  • Fabien Labernia. Algorithmes efficaces pour l'apprentissage de réseaux de préférences conditionnelles à partir de données bruitées. Intelligence artificielle [cs.AI]. PSL Research University, 2018. Français. ⟨NNT : ⟩. ⟨tel-02074097⟩