← Authors

Sayak Ray Chowdhury

20 papers · 2017–2026 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (8) πŸ—ΊοΈ Taxonomy Completionist (10) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (56) πŸ’Ž Century Club (19) πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter ⚑ Prolific Year (5)

Conferences

ICML (6) AISTATS (5) AAAI (2) ICLR (2) UAI (2) ACML (1) COLT (1) NIPS (1)

Top co-authors

Aditya Gopalan (7) Xingyu Zhou (6) Nagarajan Natarajan (3) Rafael Oliveira (2) Nishant Pandey (1) Gaurav Sinha (1) William Bankes (1) Anshul Mittal (1) Debangshu Banerjee (1) Manik Varma (1)

Research topics

Differential Privacy (3)

Keywords

regret bound (10) differential privacy (5) markov decision process (5) reproducing kernel hilbert space (5) bayesian optimization (4) reinforcement learning (3) gaussian process (3) upper confidence bound (3) policy optimization (2) regret minimization (2) kernel methods (2) heavy-tailed distribution (2) information gain (2) multi-armed bandit (2) exponential family (2) bregman divergence (1) sequential decision-making (1) kernel approximation (1) value function approximation (1) preference learning (1)

Papers

DP-NCB: Privacy Preserving Fair Bandits AAAI 2026
Right Now, Wrong Then: Non-Stationary Direct Preference Optimization under Preference Drift ICML 2025
On Differentially Private Federated Linear Contextual Bandits ICLR 2024
Differentially Private Reward Estimation with Preference Feedback AISTATS 2024
OAK: Enriching Document Representations using Auxiliary Knowledge for Extreme Classification ICML 2024
Provably Robust DPO: Aligning Language Models with Noisy Feedback ICML 2024
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference AISTATS 2023
Bregman Deviations of Generic Exponential Families COLT 2023
Distributed Differential Privacy in Multi-Armed Bandits ICLR 2023
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards ICML 2023
Combinatorial categorized bandits with expert rankings UAI 2023
Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning ACML 2022
Shuffle Private Linear Contextual Bandits ICML 2022
Differentially Private Regret Minimization in Episodic Markov Decision Processes AAAI 2022
Reinforcement Learning in Parametric MDPs with Exponential Families AISTATS 2021
No-regret Algorithms for Multi-task Bayesian Optimization AISTATS 2021
Active Learning of Conditional Mean Embeddings via Bayesian Optimisation UAI 2020
Bayesian Optimization under Heavy-tailed Payoffs NIPS 2019
Online Learning in Kernelized Markov Decision Processes AISTATS 2019
On Kernelized Multi-armed Bandits ICML 2017