News
[March 14, 2023] Talk at Huawei London.
[January 21, 2023] Our paper “Near-optimal Policy Identification in Active Reinforcement Learning” got accepted to ICLR 2023 as notable-top-5% (oral)!
[January 21, 2023] Our paper “Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning” got accepted to AISTATS 2023.
[January 12, 2023] We started an online reading group on modern adaptive experimental design and active learning in the real world.
[November 11, 2022] Talk at UCL (DeepMind/ELLIS CSML Seminar).
[October 28, 2022] Talk at Oxford Uni. (AIMS seminar).
[October 21, 2022] Talk at Imperial College London.
[October 4, 2022] Talk at Google Brain Seminar.
[September 16, 2022] Three papers got accepted to NeurIPS 2022:
- Graph Neural Network Bandits
- A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
- Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
[July 16, 2022] New paper “Graph Neural Network Bandits” is now available on arXiv.
[May 3, 2022] I gave a talk on “Learning for Reliable Decision Making” at Oracle Labs.
[May 1, 2022] We are organizing “Adaptive Experimental Design and Active Learning in the Real World” workshop at ICML2022 (Baltimore, US). Website: https://realworldml.github.io/
[February 7, 2022] New paper “A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits” is now available on arXiv.
[October 28, 2021] I gave a talk on “Corruption-tolerant Bayesian Optimization” at INFORMS Annual Meeting 2021.
[October 5, 2021] Two papers got accepted to NeurIPS 2021!
[May 10, 2021] Two papers got accepted to ICML 2021!
[March 25, 2021] Our new paper “Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning” is now available on arXiv.
[January 23, 2021] Our paper “Stochastic Linear Bandits Robust to Adversarial Attacks” got accepted to AISTATS 2021.
[October 22, 2020] Honored to receive a high-scoring reviewer award from NeurIPS2020.
[October 17, 2020] Two papers got accepted to NeurIPS 2020: “Contextual Games: Multi-Agent Learning with Side Information” and “Learning to Play Sequential Games vs. Unknown Opponents”
[May 2, 2020] In a team with Willie Neiswanger and Yisong Yue, we are organizing Workshop on Real World Experiment Design and Active Learning @ ICML 2020. See the workshop website for Cfp and more details https://realworldml.github.io/
[Mar. 8, 2020] New paper “Corruption-Tolerant Gaussian Process Bandit Optimization” is now available on arXiv.
[Mar. 4, 2020] New paper “Mixed Strategies for Robust Optimization of Unknown Objectives” is now available on arXiv.
[Mar. 3, 2020] New paper “Distributionally Robust Bayesian Optimization” is now available on arXiv.
[Jan. 6, 2019] Three papers got accepted to AISTATS 2020.
[Dec. 20, 2019] I have been awarded the ETH Postdoctoral Fellowship (ETH Fellows) for my project: “Robust Sample-Efficient Learning when Data is Costly”.
[Dec. 8-14, 2019] I am attending NeurIPS 2019, Vancouver.
[Nov. 14, 2019] I gave a talk on “Robust Sample-Efficient Learning in Uncertain Environments” at IfA (The Automatic Control Laboratory) at ETH Zurich.
[Oct. 04, 2019] I gave a nominated talk on “Robust No-regret Learning in Uncertain and Adversarial Environments” at Cornell ORIE Young Researchers Workshop.
[Sept. 04, 2019] Our paper “No-Regret Learning in Unknown Games with Correlated Payoffs” got accepted to NeurIPS 2019.
[Sept. 03, 2019] I am attending DALI2019, San Sebastian.
[Apr. 01, 2019] I joined the Learning & Adaptive Systems group (ETHZ).
Publications
Near-optimal Policy Identification in Active Reinforcement Learning
Movement Penalized Bayesian Optimization with Application to Wind Energy Systems
Graph Neural Network Bandits
A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits
Misspecified Gaussian Process Bandit Optimization
Risk-averse Heteroscedastic Bayesian Optimization
Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
DP-Sniper: Black-Box Discovery of Differential Privacy Violations using Classifiers
Stochastic Linear Bandits Robust to Adversarial Attacks
Contextual Games: Multi-Agent Learning with Side Information
Learning to Play Sequential Games versus Unknown Opponents
Corruption-Tolerant Gaussian Process Bandit Optimization
Mixed Strategies for Robust Optimization of Unknown Objectives
Distributionally Robust Bayesian Optimization
No-Regret Learning in Unknown Games with Correlated Payoffs
Overlapping Multi-Bandit Best Arm Identification
Robust Adaptive Decision Making: Bayesian Optimization and Beyond
Adversarially Robust Optimization with Gaussian Processes
High Dimensional Bayesian Optimization via Additive Models with Overlapping Groups
Robust Maximization of Non-Submodular Objectives
A Distributed Algorithm for Partitioned Robust Submodular Maximization
Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach
Robust Submodular Maximization: A Non-Uniform Partitioning Approach
Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
An Efficient Streaming Algorithm for the Submodular Cover Problem
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation
Time-Varying Gaussian Process Bandit Optimization
Learning-Based Compressive Subsampling
Active Learning of Self-concordant like Multi-index Functions
Near-Optimally Teaching the Crowd to Classify
