Publications
A better synced list after 2020 is also vailable at my HAL page.-
Thesis
-
Journal article
-
Conference article
-
Workshop article
-
Demonstration
Preprint
2024
-
, , , and ,
Augmented Bayesian Policy Search. In Proc. ICLR, 2024.
(PDF)
-
, , , and ,
Pure Exploration in Bandits with Linear Constraints. In Proc. AISTATS, 2024.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, , , , and ,
Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer. In Proc. AAMAS, 2024.
(PDF)
-
, and ,
Interactive and Concentrated Differential Privacy for Bandits. In Proc. IEEE SaTML, 2024.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, , , and ,
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption. In Proc. ALT, 2024.
(PDF)
-
, , and
2023
-
, , , and ,
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence. In Proc. NeurIPS, 2022.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, , and ,
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning. In Proc. ICML, 2023. Preprint: arXiv:2302.12559.
(PDF)
-
, , and ,
“How Biased are Your Features?”: Computing Fairness Influence Functions with Global Sensitivity Analysis. In Proc. ACM FAccT, 2023. Preprint: arXiv:2206.00667.
(PDF | Code)
-
, and ,
Marich: A Query-efficient Distributionally-Equivalent Model Extraction Attack using Public Data. In Proc. NeurIPS, 2023.
Primary version: Accepted in PPAI@AAAI, 2023.
(PDF | Code)
-
, and ,
Renyi Diffrentially Private Bandits.In PPAI@AAAI, 2023.
(PDF)
-
-
, , and
2022
-
, and ,
When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits. In Proc. NeurIPS, 2022.
Primary version: Accepted in EWRL, 2022. (PDF)
-
, and ,
Online Instrumental Variable Regression: Regret Analysis and Bandit Feedback. In HAL archives, hal-03831210, 2022.
(PDF)
-
, , , and ,
On Meritocracy in Optimal Set Selection. In Proc. ACM EAAMO, 2022.
(PDF)
-
,
,
, , and ,
On Bayesian Value Function Distributions. In EWRL, 2022. (PDF)
-
, , , and ,
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning. In Proc. UAI, 2022.
(PDF)
-
, and ,
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics. In Proc. RLDM, 2022.
Extended version: arXiv preprint, arXiv:2204.09424, 2022. (PDF)
-
, , , and ,
Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty. In OptLearnMAS Workshop@AAMAS, 2022. Extended version: arXiv preprint, arXiv:2203.10045, 2022.
(PDF)
-
, , and ,
Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback. In Proc. AAAI, 2022.
(PDF)
-
, , and ,
Algorithmic Fairness Verification with Graphical Models. In Proc. AAAI, 2022.
(PDF)
2021
-
, , and ,
UDO: Universal Database Optimization using Reinforcement Learning. In Proc. VLDB, vol. 14, September, 2021.
(PDF)
-
, , and ,
Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-based SVM. In Proc. of workshop at ECML/PKDD, September, 2021.
Presented at PharML'21. (PDF)
-
, , and ,
Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning. In Proc. SIGMOD, June, 2021.
(PDF)
-
, , , , and , Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences. In Journal of Marine Science and Engineering, February, 2021.
(PDF)
-
, , and ,
Justicia: A Stochastic SAT Approach to Formally Verify Fairness. In Proc. AAAI, February, 2021. Extended version: arXiv preprint, arXiv:2009.06516, 2020.
(PDF)
-
, , and ,
Differential Privacy at Risk: Bridging Randomness and Privacy Budget. In Proc. on Privacy Enhancing Technologies, January, 2021. (PDF)
*Extended version: arXiv preprint, arXiv:2003.00973, 2020. *Older version: In Proc. AAAI Workshop on Privacy Preserving AI (PPAI), Februray, 2020.
2020
-
,
,
, , and ,
Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning. In PMLR, Vol. 137, "I Can't Believe It's Not Better!", NeurIPS, Dec., 2020.
(PDF)
*Older version: Inferential Induction: Joint Bayesian Estimation of MDPs and Value Functions. In arXiv preprint arXiv:2002.03098, 2020.
(PDF)
-
, , , and ,
Confidentialité différentielle à risque: Relier les sources d’aléa et un budget de confidentialité. In Proc. on BDA, October, 2020. (PDF)
-
, , and ,
ε-net Induced Lazy Witness Complex on Graphs. In arXiv preprint, arXiv:2009.13071, 2020.
(PDF)
-
, , and ,
Bayesian Reinforcement Learning via Deep, Sparse Sampling. In Proc. AISTATS, Virtual, June, 2020.
(PDF)
-
, , , and ,
Construction and Random Generation of Hypergraphs with Prescribed Degree and Dimension Sequences. In Proc. DEXA, Virtual, 2020
(PDF)
-
, , and ,
Differential Privacy at Risk: Bridging Randomness and Privacy Budget. In Proc. AAAI Workshop on Privacy Preserving AI (PPAI), Februray, 2020.
(PDF)
2019
-
, , and ,
BelMan: An Information Geometric Approach to Stochastic Bandits. In Proc. ECML-PKDD, September,2019.
(PDF | Code)
-
, , and ,
ε-net Induced Lazy Witness Complex on Graphs. In Proc. ATDA at ECML-PKDD, September, 2019.
(PDF)
-
, , and ,
Differential Privacy For Multi-Armed Bandits: What Is It And What Is Its Cost?. In CORR, abs/1905.12298, 2019.
(PDF)
-
, , and ,
Near Optimal Reinforcement Learning Using Bayesian Quantiles. In CORR, abs/1906.09114, 2019.
(PDF)
-
, , and ,
Near Optimal Reinforcement Learning using Empirical Bernstein Inequalities. In CORR, abs/1906.09114, 2019.
(PDF)
-
, , and ,
Topological Data Analysis with ε-Net Induced Lazy Witness Complex. In Proc. DEXA, Linz, Austria, August, 2019.
(PDF)
-
, , and ,
Differentially Private Non-parametric Machine Learning as a Service. In Proc. DEXA, Linz, Austria, August, 2019.
(PDF)
-
, , , , , and ,
Privacy as a Service: Publishing Data and Models. In Proc. DASFAA, Thailand, April, 2019.
(PDF)
-
, , and ,
Evaluation of Differentially Private Non-parametric Machine Learning as a Service. In DSpace@NUS, 2019.
(PDF)
-
, , , , and , Learn-as-you-go with Megh: Efficient Live Migration of Virtual Machines. In IEEE Transactions on Parallel and Distributed Systems, January, 2019.
(PDF)
2018
-
,
Learning to Make Decisions with Incomplete Information: Reinforcement Learning, Information Geometry, and Real-Life Applications. In ScholarBank@NUS, October 2018.
(PDF)
-
, , and ,
Differential Privacy for Regularised Linear Regression. In Proc. DEXA, Regensburg, Germany September 2018.
(PDF)
-
, , and ,
BelMan: Bayesian Bandits on the Belief–Reward Manifold. arXiv preprint arXiv:1805.01627 2018.
(PDF | Code)
2017
-
, , , , and ,
How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough?. In Proc. DEXA, Lyon, France, August 2017.
(PDF)
-
, , , , and ,
How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough? . In Technical report, School of Computing, National University of Singapore, June 2017.
*Detailed version of DEXA 2017 paper. (PDF)
-
, , , , and , Learn-as-you-go with Megh: Efficient Live Migration of Virtual Machines. In ICDCS, Atlanta, USA, June 2017.
(PDF)
-
, , , , , and ,
Sequential Vessel Speed Optimization under Dynamic Weather Conditions. In MTEC, Singapore, April 2017.
(PDF)
2016
-
, , , and ,
Top-k Queries over Uncertain Scores. In Proc. CoopIS, Rhodes, Greece, October 2016.
(PDF)
-
, , , , and ,
Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning. Transactions on Large-Scale Data- and Knowledge-Centered Systems, Volume 28, Special Edition, LNCS 9940, 2016.
(PDF | Code)
2015
-
, , , , and ,
Apprentissage par renforcement pour optimiser les bases de donnéees indépendamment du modèle de coût. In Proc. BDA, Porquerolles, France, September 2015.
Conference without formal proceedings. (PDF | Code)
-
, , , , , , and ,
Cost-Model Oblivious Database Tuning with Reinforcement Learning. In Proc. DEXA, Valencia, Spain, September 2015.
(PDF | Code)
-
, , , ,
Interval Type-2 Fuzzy Logic Based Multiclass ANFIS Algorithm for Real-time EEG Based Movement Control of a Robot Arm. Robotics and Autonomous Systems, 68, pp. 104 - 115, June 2015.
(PDF)
2014
-
, S. Bhattacharyya, , ,
A Type-2 Adaptive Neuro-Fuzzy Inference System using Differential Evolution for EEG classification. In Proc. Fuzz-IEEE, Beijing, China,July 2014.
(PDF)
-
, , , and ,
Feature Extraction using Scale-Free Graphs for Motor Imagery EEG Signals. July 2014. Preprint.
Accepted in IEEE-SSCI, 2014 but is not in proceedings.
-
, , S. Bhattacharyya, A. Konar, A. Khasnobish, D. N. Tibarewala, and R. Janarthanan,
Embedded Realisation of Amplitude-Phase Adaptive Filter for Bio-Potential Signals. In Proc. CIEC, Kolkata, India, February 2014.
(PDF)
-
, , , and ,
A Spatially Informative Optic Flow Model of Bee Colony with Saccadic Flight Strategy for Global Optimization. IEEE Transactions on Cybernetics, vol. 44(10), pp. 593-597, January 2014.
(PDF)
2013
-
, , K. Z. Gao, and P. N. Sugnathan,
Load Information Based Priority Dependent Heuristic for Manpower Scheduling Problem in Remanufacturing. In Proc. SEMCCO, Chennai, India, December 2013.
(PDF)
-
, , K. Z. Gao, and P. N. Sugnathan,
A Novel Improved Discrete ABC Algorithm for Manpower Scheduling Problem in Remanufacturing. In Proc. SEMCCO, Chennai, India, December 2013.
(PDF)
Thesis
-
,
Learning to Make Decisions with Incomplete Information: Reinforcement Learning, Information Geometry, and Real-Life Applications. In ScholarBank, NUS, October 2018.
(PDF)
Journal articles
-
, , and
-
, , , , and , Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences. In Journal of Marine Science and Engineering, February, 2021.
(PDF)
-
, , , , and , Learn-as-you-go with Megh: Efficient Live Migration of Virtual Machines. In IEEE Transactions on Parallel and Distributed Systems, January, 2019.
(PDF)
-
, , , , and ,
Regularized Cost-Model Oblivious Database Tuning with Reinforcement Learning. Transactions on Large-Scale Data- and Knowledge-Centered Systems, Volume 28, Special Edition, LNCS 9940, 2016.
(PDF)
-
, , , ,
Interval Type-2 Fuzzy Logic Based Multiclass ANFIS Algorithm for Real-time EEG Based Movement Control of a Robot Arm. Robotics and Autonomous Systems, 68, pp. 104 - 115, June 2015.
(PDF)
-
, , , and ,
A Spatially Informative Optic Flow Model of Bee Colony with Saccadic Flight Strategy for Global Optimization. IEEE Transactions on Cybernetics, vol. 44(10), pp. 593-597, January 2014.
(PDF)
Conference articles
-
, , , and ,
Augmented Bayesian Policy Search. In Proc. ICLR, 2024.
(PDF)
-
, , , and ,
Pure Exploration in Bandits with Linear Constraints. In Proc. AISTATS, 2024.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, , , , and ,
Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer. In Proc. AAMAS, 2024.
(PDF)
-
, and ,
Interactive and Concentrated Differential Privacy for Bandits. In Proc. IEEE SaTML, 2024.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, , , and ,
CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption. In Proc. ALT, 2024.
(PDF)
-
, , , and ,
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence. In Proc. NeurIPS, 2022.
Primary version: Accepted in EWRL, 2023.
(PDF)
-
, and ,
Marich: A Query-efficient Distributionally-Equivalent Model Extraction Attack using Public Data. In Proc. NeurIPS, 2023.
Primary version: Accepted in PPAI@AAAI, 2023.
(PDF | Code)
-
, , and ,
From Noisy Fixed-Point Iterations to Private ADMM for Centralized and Federated Learning. In Proc. ICML, 2023. Preprint: arXiv:2302.12559.
(PDF)
-
, , and ,
“How Biased are Your Features?”: Computing Fairness Influence Functions with Global Sensitivity Analysis. In Proc. ACM FAccT, 2023. Preprint: arXiv:2206.00667.
(PDF | Code)
-
, , and
-
, and ,
When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits. In Proc. NeurIPS, 2022.
Primary version: Accepted in EWRL, 2022. (PDF)
-
, , , and ,
On Meritocracy in Optimal Set Selection. In Proc. ACM EAAMO, 2022.
(PDF)
-
, , , and ,
SENTINEL: Taming Uncertainty with Ensemble-based Distributional Reinforcement Learning. In Proc. UAI, 2022.
(PDF)
-
, and ,
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics. In Proc. RLDM, 2022.
Extended version: arXiv preprint, arXiv:2204.09424, 2022. (PDF)
-
, , and ,
Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-fidelity Feedback. In Proc. AAAI, 2022.
(PDF)
-
, , and ,
Algorithmic Fairness Verification with Graphical Models. In Proc. AAAI, 2022.
(PDF)
-
, , and ,
UDO: Universal Database Optimization using Reinforcement Learning. In Proc. VLDB, vol. 14, September, 2021.
(PDF)
-
, , and ,
Federated Learning of Oligonucleotide Drug Molecule Thermodynamics with Differentially Private ADMM-based SVM. In Proc. of workshop at ECML/PKDD, September, 2021.
Presented at PharML'21. (PDF)
-
, , and ,
Justicia: A Stochastic SAT Approach to Formally Verify Fairness. In Proc. AAAI, February, 2021. Extended version: arXiv preprint, arXiv:2009.06516, 2020.
(PDF)
-
, , and ,
Differential Privacy at Risk: Bridging Randomness and Privacy Budget. In Proc. on Privacy Enhancing Technologies, January, 2021. (PDF)
*Extended version: arXiv preprint, arXiv:2003.00973, 2020. *Older version: In Proc. AAAI Workshop on Privacy Preserving AI (PPAI), Februray, 2020.
-
,
,
, , and ,
Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning. In PMLR, Vol. 137, "I Can't Believe It's Not Better!", NeurIPS, Dec., 2020.
(PDF)
-
, , , and ,
Confidentialité différentielle à risque: Relier les sources d’aléa et un budget de confidentialité. In Proc. on BDA, October, 2020. (PDF)
-
, , and ,
Bayesian Reinforcement Learning via Deep, Sparse Sampling. In Proc. AISTATS, Palermo, Italy, June, 2020.
(PDF)
-
, , and ,
BelMan: An Information Geometric Approach to Stochastic Bandits. In Proc. ECML-PKDD, September,2019.
(PDF | Code)
-
, , and ,
Topological Data Analysis with ε-Net Induced Lazy Witness Complex. In Proc. DEXA, Linz, Austria, August, 2019.
(PDF)
-
, , and ,
Differentially Private Non-parametric Machine Learning as a Service. In Proc. DEXA, Linz, Austria, August, 2019.
(PDF)
-
, , , , , and ,
Privacy as a Service: Publishing Data and Models. In Proc. DASFAA, Thailand, April, 2019.
(PDF)
-
, , and ,
Differential Privacy for Regularised Linear Regression.. In Proc. DEXA, Regensburg, Germany September 2018.
(PDF)
-
, , , , and ,
How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough?. In Proc. DEXA, Lyon, France, August 2017.
(PDF)
-
, , , , and , Learn-as-you-go with Megh: Efficient Live Migration of Virtual Machines. In ICDCS, Atlanta, USA, June 2017.
(PDF)
-
, , , , , and ,
Sequential Vessel Speed Optimization under Dynamic Weather Conditions. In MTEC, Singapore, April 2017.
(PDF)
-
, , , and ,
Top-k Queries over Uncertain Scores. In Proc. CoopIS, Rhodes, Greece, October 2016.
(PDF)
-
, , , , and ,
Apprentissage par renforcement pour optimiser les bases de donnéees indépendamment du modèle de coût. In Proc. BDA, Porquerolles, France, September 2015.
Conference without formal proceedings. (PDF)
-
, , , , , , and ,
Cost-Model Oblivious Database Tuning with Reinforcement Learning. In Proc. DEXA, Valencia, Spain, September 2015.
(PDF)
-
, S. Bhattacharyya, , ,
A Type-2 Adaptive Neuro-Fuzzy Inference System using Differential Evolution for EEG classification. In Proc. Fuzz-IEEE, Beijing, China,July 2014.
(PDF)
-
, , S. Bhattacharyya, A. Konar, A. Khasnobish, D. N. Tibarewala, and R. Janarthanan,
Embedded Realisation of Amplitude-Phase Adaptive Filter for Bio-Potential Signals. In Proc. CIEC, Kolkata, India, February 2014.
(PDF)
-
, , K. Z. Gao, and P. N. Sugnathan,
A Novel Improved Discrete ABC Algorithm for Manpower Scheduling Problem in Remanufacturing. In Proc. SEMCCO, Chennai, India, December 2013.
(PDF)
-
, , K. Z. Gao, and P. N. Sugnathan,
Load Information Based Priority Dependent Heuristic for Manpower Scheduling Problem in Remanufacturing. In Proc. SEMCCO, Chennai, India, December 2013.
(PDF)
Workshop Articles (Peer-reviewed)
-
, and ,
Interactive and Concentrated Differential Privacy for Bandits. Accepted in EWRL, 2023.
(PDF)
-
, , , and ,
On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence. Accepted in EWRL, 2023.
(PDF)
-
, , , and ,
Pure Exploration in Bandits with Linear Constraints. Preprint: arXiv:2306.12774, 2023. Accepted in EWRL, 2023.
(PDF)
-
, and ,
Marich: A Query-efficient Distributionally-Equivalent Model Extraction Attack using Public Data.In PPAI@AAAI, 2023. Extended version: arXiv preprint, arXiv:2203.10045.
(PDF | Code)
-
, and ,
Renyi Diffrentially Private Bandits.In PPAI@AAAI, 2023.
(PDF)
-
-
,
,
, , and ,
On Bayesian Value Function Distributions. In EWRL, 2022. (PDF)
-
, , , and ,
Risk-Sensitive Bayesian Games for Multi-Agent Reinforcement Learning under Policy Uncertainty. In OptLearnMAS Workshop@AAMAS, 2022. Extended version: arXiv preprint, arXiv:2203.10045, 2022.
(PDF)
-
, , and ,
Differential Privacy at Risk: Bridging Randomness and Privacy Budget. In Proc. AAAI Workshop on Privacy Preserving AI (PPAI), Februray, 2020.
(PDF)
-
, , and ,
ε-net Induced Lazy Witness Complex on Graphs. In Proc. ATDA at ECML-PKDD, September, 2019.
(PDF)
Preprint (Archived Articles)
-
, and ,
Online Instrumental Variable Regression: Regret Analysis and Bandit Feedback. In HAL archives, hal-03831210, 2022.
(PDF)
-
, , and ,
ε-net Induced Lazy Witness Complex on Graphs. In arXiv preprint, arXiv:2009.13071, 2020.
(PDF)
-
, , and ,
Differential Privacy For Multi-Armed Bandits: What Is It And What Is Its Cost?. In arXiv preprint, arXiv:1905.12298, 2019.
(PDF)
-
, , and ,
Near Optimal Reinforcement Learning Using Bayesian Quantiles. In arXiv preprint, arXiv:1906.09114, 2019.
(PDF)
-
, , and ,
Near Optimal Reinforcement Learning using Empirical Bernstein Inequalities. In arXiv preprint, arXiv:1905.12425, 2019.
(PDF)
-
, , and ,
Evaluation of Differentially Private Non-parametric Machine Learning as a Service. In DSpace@NUS, 2019.
(PDF)
-
, , and ,
BelMan: Bayesian Bandits on the Belief–Reward Manifold. In arXiv preprint, arXiv:1805.01627 2018.
(PDF)
-
, , , , and ,
How to Find the Best Rated Items on a Likert Scale and How Many Ratings Are Enough? . In Technical report, School of Computing, National University of Singapore, June 2017.
*Detailed version of DEXA 2017 paper. (PDF)
-
, , , and ,
Feature Extraction using Scale-Free Graphs for Motor Imagery EEG Signals. July 2014. Preprint.
Accepted in IEEE-SSCI, 2014 but is not in proceedings.