CV Accueil - Archive ouverte HAL

	Differential Privacy at Risk: Bridging Randomness and Privacy Budget Ashish Dandekar , Debabrota Basu , Stéphane Bressan Proceedings on Privacy Enhancing Technologies, 2021, 2021 (1), pp.64-84. ⟨10.2478/popets-2021-0005⟩ Article dans une revue hal-02942997v1
	Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences Igor Ryazanov , Amanda Nylund , Debabrota Basu , Ida-Maja Hassellöv , Alexander Schliep Journal of Marine Science and Engineering, 2021, 9 (2), pp.169. ⟨10.3390/jmse9020169⟩ Article dans une revue hal-03445756v1

	Interactive and Concentrated Differential Privacy for Bandits Achraf Azize , Debabrota Basu EWRL 2023 – European Workshop on Reinforcement Learning, Sep 2023, Brussels (Belgium), Belgium Communication dans un congrès hal-04215685v1
	"How Biased are Your Features?": Computing Fairness Influence Functions with Global Sensitivity Analysis Bishwamittra Ghosh , Debabrota Basu , Kuldeep Meel FAccT '23: the 2023 ACM Conference on Fairness, Accountability, and Transparency, Jun 2023, Chicago IL, United States. pp.138-148, ⟨10.1145/3593013.3593983⟩ Communication dans un congrès hal-03770346v1
	Farm-gym: A modular reinforcement learning platform for stochastic agronomic games Odalric-Ambrym Maillard , Timothée Mathieu , Debabrota Basu AIAFS 2023 - Artificial Intelligence for Agriculture and Food Systems, Feb 2023, Wahington DC, United States Communication dans un congrès hal-03960683v1
	From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning Edwige Cyffers , Aurélien Bellet , Debabrota Basu Proceedings of the 40th International Conference on Machine Learning (ICML), Jul 2023, Honolulu, United States Communication dans un congrès hal-04260417v1
	Pure Exploration in Bandits with Linear Constraints Emil Carlsson , Debabrota Basu , Fredrik D. Johansson , Devdatt Dubhashi EWRL 2023 – European Workshop on Reinforcement Learning, Sep 2023, Brussels, Belgium Communication dans un congrès hal-04203235v1
	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 Communication dans un congrès hal-04215474v1
	Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data Pratik Karmakar , Debabrota Basu Advances in Neural Information Processing Systems (NeurIPS), Dec 2023, New orleans, USA, United States Communication dans un congrès hal-04260442v1
	Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning Reda Ouhamma , Debabrota Basu , Odalric-Ambrym Maillard Proceedings of the AAAI Conference on Artificial Intelligence, Feb 2023, Washignton DC, United States. pp.9336-9344, ⟨10.1609/aaai.v37i8.26119⟩ Communication dans un congrès hal-03790997v2
	On Meritocracy in Optimal Set Selection Thomas Kleine Buening , Meirav Segal , Debabrota Basu , Anne-Marie George , Christos Dimitrakakis EAAMO 2022- Equity and Access in Algorithms, Mechanisms, and Optimization, ACM, Oct 2022, Arlington, United States Communication dans un congrès hal-03445971v1
	UDO: Universal Database Optimization using Reinforcement Learning Junxiong Wang , Immanuel Trummer , Debabrota Basu Proceedings of the VLDB Endowment, Sep 2022, Sydney, Australia. pp.3402-3414, ⟨10.14778/3484224.3484236⟩ Communication dans un congrès hal-03445686v1
	Algorithmic fairness verification with graphical models Bishwamittra Ghosh , Debabrota Basu , Kuldeep S. Meel AAAI-2022 - 36th AAAI Conference on Artificial Intelligence, Feb 2022, Virtual, United States Communication dans un congrès hal-03770361v1
	When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits Achraf Azize , Debabrota Basu Advances in Neural Information Processing Systems, Dec 2022, New Orleans, United States Communication dans un congrès hal-03781600v1
	Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty Hannes Eriksson , Debabrota Basu , Mina Alibeigi , Christos Dimitrakakis OptLearnMAS@AAMAS, May 2022, Virtual, New Zealand Communication dans un congrès hal-03770369v1
	SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning Hannes Eriksson , Debabrota Basu , Mina Alibeigi , Christos Dimitrakakis UAI 2022- Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, Aug 2022, Eindhoven, Netherlands. pp.631-640 Communication dans un congrès hal-03150823v2
	SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics Yannis Flet-Berliac , Debabrota Basu RLDM 2022 - The Multi-disciplinary Conference on Reinforcement Learning and Decision Making, Jun 2022, Providence, United States Communication dans un congrès hal-03771734v1
	Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback Junxiong Wang , Debabrota Basu , Immanuel Trummer AAAI Conference on Artificial Intelligence, Feb 2022, Virtual, United States. pp.10381-10390 Communication dans un congrès hal-03445909v1
	Justicia: A Stochastic SAT Approach to Formally Verify Fairness Bishwamittra Ghosh , Debabrota Basu , Kuldeep S. Meel AAAI Conference on Artificial Intelligence, Feb 2021, Virtual, Canada. pp.7554-7563 Communication dans un congrès hal-03445831v1
	Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning Junxiong Wang , Immanuel Trummer , Debabrota Basu SIGMOD/PODS '21: International Conference on Management of Data, Jun 2021, Virtual Event, China. pp.2794-2797, ⟨10.1145/3448016.3452754⟩ Communication dans un congrès hal-03446016v1
	Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning Emilio Jorge , Hannes Eriksson , Christos Dimitrakakis , Debabrota Basu , Divya Grover "I Can't Believe It's Not Better!" at NeurIPS Workshops, Dec 2020, Vancouver, Canada. pp.43-52 Communication dans un congrès hal-03125100v1
	Construction and Random Generation of Hypergraphs with Prescribed Degree and Dimension Sequences Naheed Anjum Arafat , Debabrota Basu , Laurent Decreusefond , Stéphane Bressan DEXA, 2020, Bratislava, Slovenia Communication dans un congrès hal-02541206v1
	Confidentialité différentielle à risque : Relier les sources d’aléa et un budget de confidentialité Ashish Dandekar , Debabrota Basu , Pierre Senellart , Stéphane Bressan BDA 2020 - 36ème Conférence sur la Gestion de Données – Principes, Technologies et Applications, Oct 2020, Paris / Virtuel, France Communication dans un congrès hal-03103528v1
	BelMan: An Information-Geometric Approach to Stochastic Bandits Debabrota Basu , Pierre Senellart , Stéphane Bressan ECML/PKDD - The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2019, Würzburg, Germany Communication dans un congrès hal-02195539v1
	How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough Qing Liu , Debabrota Basu , Shruti Goel , Talel Abdessalem , Stéphane Bressan Database and Expert Systems Applications - 28th International Conference, DEXA 2017, Lyon, France, August 28-31, 2017, Proceedings, Part II, 2017, Lyon, France. pp.351-359, ⟨10.1007/978-3-319-64471-4_28⟩ Communication dans un congrès hal-02412320v1
	Top-k Queries Over Uncertain Scores Qing Liu , Debabrota Basu , Talel Abdessalem , Stéphane Bressan On the Move to Meaningful Internet Systems (OTM-CoopIS 2016), Oct 2016, Rhodes, Greece. pp.245-262, ⟨10.1007/978-3-319-48472-3_14⟩ Communication dans un congrès hal-01700174v1
	Cost-Model Oblivious Database Tuning with Reinforcement Learning Debabrota Basu , Qian Lin , Weidong Chen , Hoang Tam Vo , Zihong Yuan DEXA, Sep 2015, Valencia, Spain. pp.253-268 Communication dans un congrès hal-01261945v1
	Apprentissage par renforcement pour optimiser les bases de donnéees indépendamment du modèle de coût Debabrota Basu , Qian Lin , Zihong Yuan , Pierre Senellart , Stéphane Bressan BDA, Sep 2015, Porquerolles, France Communication dans un congrès hal-02287156v1

	Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-Based SVM Shirin Tavara , Alexander Schliep , Debabrota Basu Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 1525, Springer International Publishing; Springer International Publishing, pp.459-467, 2021, Communications in Computer and Information Science, ⟨10.1007/978-3-030-93733-1_34⟩ Chapitre d'ouvrage hal-03841224v1
	Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning Debabrota Basu , Qian Lin , Weidong Chen , Hoang Tam Vo , Zihong Yuan Abdelkader Hameurlain; Josef Küng; Roland Wagner; Qimin Chen. Transactions on Large-Scale Data- and Knowledge-Centered Systems XXVIII, 9940, Springer Verlag, pp.96-132, 2016, Lecture Notes in Computer Science, ⟨10.1007/978-3-662-53455-7_5⟩ Chapitre d'ouvrage hal-02115175v1

	Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer Hannes Eriksson , Debabrota Basu , Tommy Tram , Mina Alibeigi , Christos Dimitrakakis 2023 Pré-publication, Document de travail hal-04260795v1
	CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption Shubhada Agrawal , Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard 2023 Pré-publication, Document de travail hal-04260464v1
	Online Instrumental Variable Regression: Regret Analysis and Bandit Feedback Riccardo Della Vecchia , Debabrota Basu 2023 Pré-publication, Document de travail hal-03831210v2
	Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithm Debabrota Basu , Odalric-Ambrym Maillard , Timothée Mathieu 2022 Pré-publication, Document de travail hal-03611816v1
	BelMan: Bayesian Bandits on the Belief--Reward Manifold Debabrota Basu , Pierre Senellart , Stéphane Bressan 2018 Pré-publication, Document de travail hal-01891813v1

Debabrota Basu

Publications

Differential Privacy at Risk: Bridging Randomness and Privacy Budget

Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences

Interactive and Concentrated Differential Privacy for Bandits

"How Biased are Your Features?": Computing Fairness Influence Functions with Global Sensitivity Analysis

Farm-gym: A modular reinforcement learning platform for stochastic agronomic games

From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning

Pure Exploration in Bandits with Linear Constraints

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

Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data

Bilinear Exponential Family of MDPs: Frequentist Regret Bound with Tractable Exploration & Planning

On Meritocracy in Optimal Set Selection

UDO: Universal Database Optimization using Reinforcement Learning

Algorithmic fairness verification with graphical models

When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits

Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty

SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning

SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics

Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback

Justicia: A Stochastic SAT Approach to Formally Verify Fairness

Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning

Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning

Construction and Random Generation of Hypergraphs with Prescribed Degree and Dimension Sequences

Confidentialité différentielle à risque : Relier les sources d’aléa et un budget de confidentialité

BelMan: An Information-Geometric Approach to Stochastic Bandits

How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough

Top-k Queries Over Uncertain Scores

Cost-Model Oblivious Database Tuning with Reinforcement Learning

Apprentissage par renforcement pour optimiser les bases de donnéees indépendamment du modèle de coût

Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-Based SVM

Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning

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

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

Online Instrumental Variable Regression: Regret Analysis and Bandit Feedback

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

BelMan: Bayesian Bandits on the Belief--Reward Manifold