Awarded by the graduate program in computer science, more info here: https://pginfo.ens.psl.eu/2023/call_phd_en.html
Two papers co-authored by MILES members have been accepted to the 2023 of ICLR (International Conference on Learning Representations):
- Contextual bandits with concave rewards, and an application to fair ranking, by Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric and Nicolas Usunier;
- A unified algebraic perspective on Lipschitz neural networks, by Alexandre Araujo (MILES alumni), Aaron J. Havens, Blaise Delattre, Alexandre Allauzen and Bin Hu.
Congratulations to all!
Six papers featuring members of MILES (and very recent alumni) were accepted at NeurIPS 2022, one of the flagship conferences in machine learning! Below are the papers (with MILES authors in bold)
- Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions by Lucas Baudin and Rida Laraki
- An α-No-Regret Algorithm For Graphical Bilinear Bandits by Geovani Rizk, Igor Colin, Albert Thomas, Rida Laraki and Yann Chevaleyre
- Towards Consistency in Adversarial Classification by Laurent Meunier (recent MILES alumni), Raphael Ettedgui, Rafael Pinot (former MILES member), Yann Chevaleyre and Jamal Atif
- Benchopt: Reproducible, efficient and collaborative optimization benchmarks by Thomas Moreau et al, featuring Pierre Ablin (recent MILES alumni)
- Do Residual Neural Networks discretize Neural Ordinary Differential Equations? by Michael E. Sander, Pierre Ablin (recent MILES alumni) and Gabriel Peyré
- A framework for bilevel optimization that enables stochastic and global variance reduction algorithms by Matthieu Dagréou, Pierre Ablin (recent MILES alumni), Samuel Vaiter, Thomas Moreau.
Congratulations to all, and kudos to all authors who submitted at NeurIPS this year!
MILES has the great pleasure of hosting Dr. Makoto Yamada on September 22 for a guest seminar!
Title: Approximating 1-Wasserstein Distance with Trees
Abstract: Wasserstein distance, which measures the discrepancy between distributions, shows efficacy in various types of natural language processing (NLP) and computer vision (CV) applications. One of the challenges in estimating Wasserstein distance is that it is computationally expensive and does not scale well for many distribution comparison tasks. In this talk, I propose a learning-based approach to approximate the 1-Wasserstein distance with trees. Then, I demonstrate that the proposed approach can accurately approximate the original 1-Wasserstein distance for NLP tasks. (https://arxiv.org/abs/2206.12116)
Speaker bio: Makoto Yamada received the Ph.D. degree in statistical science from The Graduate University for Advanced Studies (SOKENDAI, The Institute of Statistical Mathematics), Tokyo, in 2010. Currently, he is a team leader at RIKEN AIP, an associate professor at Kyoto University, and a transitional associate professor at Okinawa Institute of Science and Technology (OIST). His research interests include machine learning and its application to biology, natural language processing, and computer vision. He published more than 50 research papers in premium conferences and journals such as NeurIPS, AISTATS, ICML, AAAI, IJCAI, and TPAMI, and won the WSDM 2016 Best Paper Award.
The seminar will take place on September 22 at 3pm in room A707 of Université Paris Dauphine-PSL.
MILES is thrilled to welcome Pierre Ablin as a new CNRS researcher within the team!
Pierre’s research interests revolve around optimization, machine learning, neural networks and brain signal processing. Stay tuned for more updates about Pierre’s research!
As part of its weekly group meeting, MILES is glad to announce three seminars in the upcoming weeks!
- September 30, 2021: In-person seminar by Ruben Ohana (ENS & LightOn)
Training neural networks with Direct Feedback Alignment: theory and applications in adversarial robustness
- October 7, 2021: In-person seminar by Laurent Daudet (LightOn)
Optical random projections: scaling up randomized algorithms for scientific computing and machine learning
- October 14, 2021: Online seminar by Lindon Roberts (ANU, Australia)
Inexact Derivative-Free Optimization for Bilevel Learning
Want to give a seminar for our group and beyond? Please send an email at firstname.lastname@example.org.
Three papers from MILES researchers have been accepted to the 2021 International Conference on Machine Learning (ICML), one of the most prestigious venues for data science:
- Mixed Nash Equilibria in the Adversarial Examples Game co-authored by Laurent Meunier, Rafael Pinot (former MILES member), Jamal Atif and Yann Chevaleyre;
- Mediated uncoupled learning: Learning functions without direct input-output correspondences, co-authored by Ikko Yamane and Florian Yger;
- Best Arm Identification in Graphical Bilinear Bandits, co-authored by Geovani Rizk, Rida Laraki and Yann Chevaleyre.
In addition, Clément Royer will be a featured speaker at the ICML 2021 workshop Beyond first-order methods in ML systems.
Last but certainly not least, Alexandre Vérine will present the paper On the expressivity of bi-Lipschitz normalizing flows (a full MILES collaborative effort together with Benjamin Negrevergne, Fabrice Rossi and Yann Chevaleyre) at the ICML 2021 workshop Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models.
Feel free to contact MILES researchers to catch them during ICML!
Rafael Pinot is a recipient of the 2021 Prix Jeune Chercheur (Young Researcher Prize) from the Dauphine Foundation. This prize is awarded every year to the top PhD graduates in Dauphine (see here for a formal description in French).
Rafael defended his PhD thesis on December 12, 2020. He was co-supervised by Jamal Atif and Florian Yger at MILES, as well as Cédric Gouy-Pailler at CEA-LIST. Rafael is now a postdoctoral researcher at École Polytechnique Fédérale de Lausanne, but we are happy to welcome him back on June 28 as he visits Dauphine to receive his prize. Congratulations!
Congratulations to Virginie Do, Jamal Atif and Jérôme Lang for getting a paper accepted in the 30th International Joint Conference on Artificial Intelligence (IJCAI).
Their paper, Online Selection of Diverse Committees, co-authored with Nicolas Usunier from Facebook AI Research, can be accessed here.
A two-year postdoctoral position in optimization for high-performance artificial intelligence is available in MILES!
The successful applicant will conduct their research in collaboration with Clément W. Royer, but interactions with other MILES members will be strongly encouraged. The position is expected to start in the Fall of 2021.
For more information, see the full job description here. Do not hesitate to contact Clément W. Royer for any questions!