Selected Publications
- Delayed Feedback in Kernel Bandits, ICML 2023.
- Provably and Practically Efficient Neural Contextual Bandits, ICML 2023.
- Image generation with shortest path diffusion, ICML 2023.
- Sample Complexity of Kernel-Based Q-Learning, AISTATS 2023
- Fisher-Legendre (FishLeg) optimization of deep neural networks, ICLR 2023
- Uniform generalization bounds for overparameterized neural networks, ISIT 2023
- Near-Optimal Collaborative Learning in Bandits, NeurIPS 2022
- Improved convergence rates for sparse approximation methods in kernel-based learning, ICML 2022
- On Information Gain and Regret Bounds in GP Bandits, AISTATS 2021, [slides], [presentation]
- Optimal order simple regret for GP bandits, NeurIPS 2021, [slides], [presentation]
- Scalable Thompson sampling using sparse Gaussian process models, NeurIPS 2021, [slides], [presentation]
- Open problem: Tight online confidence intervals for RKHS elements, COLT 2021, [slides], [presentation]
- A domain-shrinking based Bayesian optimization algorithm with orderoptimal regret performance, NeurIPS 2021
- Stochastic Coordinate Minimization with Progressive Precision for Stochastic Convex Optimization, ICML 2020
- Amortized variance reduction for doubly stochastic objective, UAI 2020
- Adaptive sensor placement for continuous spaces, ICML 2019
- Multi-armed bandits on partially revealed unit interval graphs, IEEE Transactions on Network Science and Engineering 2019
- A random walk approach to first-order stochastic convex optimization, ISIT 2019
- Decision variance in risk-averse online learning, CDC 2019
- Hierarchical heavy hitter detection under unknown models, ICASSP 2018
- Online learning with side information, MILCOM 2017
- Risk-averse multi-armed bandit problems under mean-variance measure, Journal of Slected Topic in Signal Processing 2016
- Quickest detection of short-term voltage instability with PMU measurements, ICASSP 2015
- Time-varying stochastic multi-armed bandit problems, Asilomar 2014
- Deterministic sequencing of exploration and exploitation for multi-armed bandit problems, Journal of Selected Topics in Signal Processing 2013
- Achieving complete learning in multi-armed bandit problems, Asilomar 2013