TALKS
Invited TalkS
March 2024: Provably Robust DPO: Aligning Language Models with Noisy Preferences. Center for Networked Intelligence, IISc Bangalore, India. Video link
August 2023: Differential Privacy in Multi-armed Bandits. Theory Seminar, Dept of CSA, IISc Bangalore, India. Video link
June 2023: Differential Privacy in Reinforcement Learning. Machine Learning Summer School for Science, Jagiellonian University, Poland. Video link
November 2022: Time Uniform Concentration Bounds for Black Box Optimization. IEEE Information Theory Workshop (ITW), IIT Bombay, India.
July 2022: Shuffle private Linear Contextual Bandits. Network Seminar, Center for Networked Intelligence, IISc Bangalore, India. Video link
October 2021: Reinforcement Learning in Large and Structured Environments. Department of ECE, Boston University, USA.
July 2019: Tuning Hyperparameters with Bayesian Optimization. Google PhD Fellowship Summit, Mountainview, USA.
August 2018: Bayesian Optimization meets Reinforcement Learning. Google PhD Fellowship Summit, Mountainview, USA.
Jan 2018: On Kernelized Multi-armed Bandits. Google Research, Bangalore, India.
contributed TalkS / PREsentations
July 2023: Bregman Deviations of Generic Exponential Families. COLT, Bangalore, India.
July 2023: Differentially Private Reward Estimation from Preference-based Feedback. ICML Workshop, Honolulu, USA.
July 2023: On Differentially Private Federated Linear Contextual Bandits. ICML Workshop, Honolulu, USA.
Dec 2022: Value Function Approximations via Kernel Embeddings for No-Regret Reinforcement Learning. ACML, Hyderabad, India.
March 2022: Online Reinforcement Learning in Large and Structured Environments. Thesis Defence, IISc Bangalore, India.
April 2021: Reinforcement Learning in Parametric MDPs with Exponential Families. AISTATS, virtual.
April 2021: No-regret Algorithms for Multi-task Bayesian Optimization. AISTATS, virtual.
Dec 2019: Bayesian Optimization under Heavy-tailed Payoffs. NeurIPS, Vancouver, Canada.
April 2019: Online Learning in Kernelized Markov Decision Processes. AISTATS, Naha, Okinawa, Japan.
Dec 2018: On Batch Bayesian Optimization. NeurIPS workshop, Montreal, Canada.
Dec 2018: Online Learning in Kernelized Markov Decision Processes. NeurIPS workshop, Montreal, Canada.
August 2017: On Kernelized Multi-armed Bandits. ICML, Sydney, Australia.