Recherche - Université de Lille

Filtrer vos résultats

20 résultats
Image document

A PAC-Bayesian Link Between Generalisation and Flat Minima

Maxime Haddouche , Paul Viallard , Umut Şimşekli , Benjamin Guedj
2024
Pré-publication, Document de travail hal-04455639v1

When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning

Naheed Anjum Arafat , Debabrota Basu , Yulia Gel , Yuzhou Chen
2024
Pré-publication, Document de travail hal-04708183v1

Learning to Explore with Lagrangians for Bandits under Unknown Linear Constraints

Udvas Das , Debabrota Basu
Seventeenth European Workshop on Reinforcement Learning (EWRL), Oct 2024, Toulouse, France
Communication dans un congrès hal-04784911v1
Image document

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm

Batiste Le Bars , Aurélien Bellet , Marc Tommasi , Kevin Scaman , Giovanni Neglia
ICML 2024 - The Forty-first International Conference on Machine Learning, Jul 2024, Vienne, Austria
Communication dans un congrès hal-04611418v1
Image document

Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithms

Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard
Transactions on Machine Learning Research Journal, 2024
Article dans une revue hal-04615733v1
Image document

Open Problem: What is the Complexity of Joint Differential Privacy in Linear Contextual Bandits?

Achraf Azize , Debabrota Basu
Proceedings of Thirty Seventh Conference on Learning Theory, Jul 2024, Edmonton (Alberta), Canada
Communication dans un congrès hal-04621903v1

Measuring Exploration in Reinforcement Learning via Optimal Transport in Policy Space

Reabetswe M. Nkhumise , Debabrota Basu , Tony J. Prescott , Aditya Gilra
2024
Pré-publication, Document de travail hal-04702986v1

Active Fourier Auditor for Estimating Distributional Properties of ML Models

Ayoub Ajarra , Bishwamittra Ghosh , Debabrota Basu
2024
Pré-publication, Document de travail hal-04733059v1

Concentrated Differential Privacy for Bandits

Achraf Azize , Debabrota Basu
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), IEEE, Apr 2024, Toronto, Canada. pp.78-109, ⟨10.1109/SaTML59370.2024.00013⟩
Communication dans un congrès hal-04611650v1

Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs

Chao Han , Debabrota Basu , Michael Mangan , Eleni Vasilaki , Aditya Gilra
2024
Pré-publication, Document de travail hal-04785076v1
Image document

Asynchronous Multi-fidelity Hyperparameter Optimization Of Spiking Neural Networks

Thomas Firmin , Pierre Boulet , El-Ghazali Talbi
International Conference on Neuromorphic Systems (ICONS 2024), Jul 2024, Washington, United States
Communication dans un congrès hal-04781629v1

Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer

Hannes Eriksson , Tommy Tram , Debabrota Basu , Mina Alibeigi , Christos Dimitrakakis
23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2024, Auckland, New Zealand. pp.516-524, ⟨10.5555/3635637.3662902⟩
Communication dans un congrès hal-04260795v1

FLIPHAT: Joint Differential Privacy for High Dimensional Sparse Linear Bandits

Sunrit Chakraborty , Saptarshi Roy , Debabrota Basu
2024
Pré-publication, Document de travail hal-04615697v1

CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption

Shubhada Agrawal , Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard
International Conference on Algorithmic Learning Theory (ALT), Feb 2024, San Diego (CA), United States. pp.74-124
Communication dans un congrès hal-04260464v1

Differentially Private Best-Arm Identification

Achraf Azize , Marc Jourdan , Aymen Al Marjani , Debabrota Basu
2024
Pré-publication, Document de travail hal-04615690v1

Tighter Generalisation Bounds via Interpolation

Paul Viallard , Maxime Haddouche , Umut Şimşekli , Benjamin Guedj
2024
Pré-publication, Document de travail hal-04456925v1

Testing Credibility of Public and Private Surveys through the Lens of Regression

Debabrota Basu , Sourav Chakraborty , Debarshi Chanda , Buddha Dev Das , Arijit Ghosh , et al.
2024
Pré-publication, Document de travail hal-04733076v1

On the Impact of Output Perturbation on Fairness in Binary Linear Classification

Vitalii Emelianov , Michaël Perrot
2024
Pré-publication, Document de travail hal-04440982v1
Image document

Preference-based Pure Exploration

Apurv Shukla , Debabrota Basu
Advances in Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver (CA), Canada
Communication dans un congrès hal-04733134v1

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

Achraf Azize , Marc Jourdan , Aymen Al Marjani , Debabrota Basu
NeurIPS 2023 – Conference on Neural Information Processing Systems, Dec 2023, New Orleans (US), United States. pp.71150--71194
Communication dans un congrès hal-04215474v1