I am a postdoctoral researcher at the ETH Learning & Adaptive Systems group led by Prof. Andreas Krause.
Interests
- Machine Learning
- Algorithms and Theory
- Optimization
Education
-
PhD in Computer and Communication Sciences
EPFL Lausanne
-
MSc in Computer Science
ETH Zurich
-
BSc in Electrical Engineering
University of Novi Sad
News
[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
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
