This year, several researchers from CREST will present their papers to the International Conference on Machine Learning (ICML) which will occur from July 21st to 27th.
About ICML
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.
ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.
ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
CREST’s papers to be presented
1. A connection between Tempering and Entropic Mirror Descent
Nicolas Chopin, Francesca R Crucinio, Anna Korba
2. Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
Tom Huix, Eric Moulines, Alain Oliviero Durmus, Anna Korba
3. Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman
4. A New Branch-and-Bound Pruning Framework for $ell_0$-Regularized Problems
Guyard Theo, Cédric Herzet, Clément Elvira, Ayse-Nur Arslan
5. Active Ranking and Matchmaking, with Perfect Matchings
Hafedh Ferchichi, Matthieu LERASLE, Vianney Perchet
6. Non-clairvoyant Scheduling with Partial Predictions
Ziyad Benomar, Vianney Perchet
7. Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Elen Vardanyan, Sona Hunanyan, Arnak Dalalyan, Tigran Galstyan, Arshak Minasyan
8. On a Neural Implementation of Brenier’s Polar Factorization
Nina Vesseron, Marco Cuturi
Click here for more information about the conference.
8 CREST papers to be presented at ICML 2024
This year, several researchers from CREST will present their papers to the International Conference on Machine Learning (ICML) which will occur from July 21st to 27th.
About ICML
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning.
ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.
ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
CREST’s papers to be presented
1. A connection between Tempering and Entropic Mirror Descent
Nicolas Chopin, Francesca R Crucinio, Anna Korba
2. Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
Tom Huix, Eric Moulines, Alain Oliviero Durmus, Anna Korba
3. Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates
Rémi Leluc, Aymeric Dieuleveut, François Portier, Johan Segers, Aigerim Zhuman
4. A New Branch-and-Bound Pruning Framework for $\ell_0$-Regularized Problems
Guyard Theo, Cédric Herzet, Clément Elvira, Ayse-Nur Arslan
5. Active Ranking and Matchmaking, with Perfect Matchings
Hafedh Ferchichi, Matthieu LERASLE, Vianney Perchet
6. Non-clairvoyant Scheduling with Partial Predictions
Ziyad Benomar, Vianney Perchet
7. Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution
Elen Vardanyan, Sona Hunanyan, Arnak Dalalyan, Tigran Galstyan, Arshak Minasyan
8. On a Neural Implementation of Brenier’s Polar Factorization
Nina Vesseron, Marco Cuturi
Click here for more information about the conference.
Beyond the PhD – CREST Series 2: How would you define a PhD?
Last year, CREST introduced a new series of videos on the PhD theme. Léa Bou Sleiman & Martin Mugnier were interviewed for this first episode of “Beyond the PhD”. The 4th year economics PhD students present their career at CREST and their participation in the International Job Market.
In 2024, the Beyond the PhD series is focused on the definition of a PhD.
In doing so, four PhD students from CREST have participated in this interview series:
- Reda Alami Chentoufi, 1st year PhD student in Finance-Insurance (CREST-GENES)
- Emma Bonutti d’Agostini, 1st year PhD student in Sociology (CREST-GENES)
- Yiyun Zheng, 2nd year PhD student in Economics (CREST-Ecole polytechnique)
- Clara Carlier, 3rd year PhD student in Statistics (CREST-GENES)
With the participation of Prof. Emmanuelle Taugourdeau, Research Director at CNRS and Deputy Director at CREST, all four PhD students answered some questions about the PhD program: how would they describe it, what is of importance in a PhD and their recommendations to future PhD students.
All videos are now available on the CREST’s YouTube account.
We want here to promote the interview highlights that key points of all interviews in one.
Below, you will find all videos available in the scope of the Beyond the PhD video series 2.
Beyond the PhD – CREST Series 2: How would you define a PhD?
Last year, CREST introduced a new series of videos on the PhD theme. Léa Bou Sleiman & Martin Mugnier were interviewed for this first episode of “Beyond the PhD”. The 4th year economics PhD students present their career at CREST and their participation in the International Job Market.
In 2024, the Beyond the PhD series is focused on the definition of a PhD.
In doing so, four PhD students from CREST have participated in this interview series:
- Reda Alami Chentoufi, 1st year PhD student in Finance-Insurance (CREST-GENES)
- Emma Bonutti d’Agostini, 1st year PhD student in Sociology (CREST-GENES)
- Yiyun Zheng, 2nd year PhD student in Economics (CREST-Ecole polytechnique)
- Clara Carlier, 3rd year PhD student in Statistics (CREST-GENES)
With the participation of Prof. Emmanuelle Taugourdeau, Research Director at CNRS and Deputy Director at CREST, all four PhD students answered some questions about the PhD program: how would they describe it, what is of importance in a PhD and their recommendations to future PhD students.
All videos are now available on the CREST’s YouTube account.
We want here to promote the interview highlights that key points of all interviews in one.
Below, you will find all videos available in the scope of the Beyond the PhD video series 2.
Une interview de Vianney Perchet, coordinateur du projet BOLD, qui vise à améliorer l’apprentissage séquentiel
Une interview de Vianney Perchet, coordinateur du projet BOLD, qui vise à améliorer l’apprentissage séquentiel
18.04.2024
Une interview de Vianney Perchet, coordinateur du projet BOLD, qui vise à améliorer l’apprentissage séquentiel
Une interview de Vianney Perchet, coordinateur du projet BOLD, qui vise à améliorer l’apprentissage séquentiel
18.04.2024
Arnak Dalalyan and Vianney Perchet nominated as new members of the editorial board of the journal “Foundations and Trends® in Machine Learning”.
Arnak Dalalyan and Vianney Perchet nominated as new members of the editorial board of the journal “Foundations and Trends® in Machine Learning”.
Arnak Dalalyan and Vianney Perchet nominated as new members of the editorial board of the journal “Foundations and Trends® in Machine Learning”.
Arnak Dalalyan and Vianney Perchet nominated as new members of the editorial board of the journal “Foundations and Trends® in Machine Learning”.
Catalyzing Conversation: The Royal Statistical Society’s Webinar on Dalalyan’s Paper ‘Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities'”
On 31 October, the Royal Statistical Society webinar was devoted to Arnak S. Dalalyan’s 2017 Series B paper ‘Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities’, featuring contributions from Hani Doss and Alain Durmus.
“[Dalalyan] combines techniques from convex optimisation with insights from random processes to provide non-asymptotic guarantees regarding the accuracy of sampling from a target probability density. These guarantees are notably simpler than those found in the existing literature, and they remain unaffected by dimensionality.
The findings pave the way for more widespread adoption of the mathematical and algorithmic tools developed in the field of convex optimization within the domains of statistics and machine learning.”
Showcasing significant recent papers published in the Society’s journals, the journal webinar format aims to bring authors closer to their audience in academia and industry. Impactful features of the paper are presented by the author, followed by contributions from the guest discussants.
Catalyzing Conversation: The Royal Statistical Society’s Webinar on Dalalyan’s Paper ‘Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities'”
On 31 October, the Royal Statistical Society webinar was devoted to Arnak S. Dalalyan’s 2017 Series B paper ‘Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities’, featuring contributions from Hani Doss and Alain Durmus.
“[Dalalyan] combines techniques from convex optimisation with insights from random processes to provide non-asymptotic guarantees regarding the accuracy of sampling from a target probability density. These guarantees are notably simpler than those found in the existing literature, and they remain unaffected by dimensionality.
The findings pave the way for more widespread adoption of the mathematical and algorithmic tools developed in the field of convex optimization within the domains of statistics and machine learning.”
Showcasing significant recent papers published in the Society’s journals, the journal webinar format aims to bring authors closer to their audience in academia and industry. Impactful features of the paper are presented by the author, followed by contributions from the guest discussants.