5 papers
Learning Kernel-Based MDPs from Episodic Preferential Feedback
Nikola Pavlovic, Sattar Vakili, Qing Zhao
Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also referred to as reinforcement…
Differential Privacy in Kernelized Contextual Bandits via Random Projections
Nikola Pavlovic, Sudeep Salgia, Qing Zhao
We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space. We study th…
Differentially Private Kernelized Contextual Bandits
Nikola Pavlovic, Sudeep Salgia, Qing Zhao
We consider the problem of contextual kernel bandits with stochastic contexts, where the underlying reward function belongs to a known Reproducing Kernel Hilbert Space (RKHS). We s…
Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization
Sudeep Salgia, Nikola Pavlovic, Yuejie Chi +1
We consider the problem of differentially private stochastic convex optimization (DP-SCO) in a distributed setting with clients, where each of them has a local dataset of i…
Order-Optimal Regret in Distributed Kernel Bandits using Uniform Sampling with Shared Randomness
Nikola Pavlovic, Sudeep Salgia, Qing Zhao
We consider distributed kernel bandits where agents aim to collaboratively maximize an unknown reward function that lies in a reproducing kernel Hilbert space. Each agent seque…