Publications
See also my Google Scholar profile.
AISTATS
Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits
International Conference on Artificial Intelligence and Statistics, 2026
Oral Presentation (top 10 / ~2100)
ICLR
Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models
International Conference on Learning Representations, 2026
WINE
Misalignment, Learning, and Ranking: Harnessing Users Limited Attention
Web and Internet Economics, 2025
TMLR
Non-Stationary Dueling Bandits Under a Weighted Borda Criterion
Transactions on Machine Learning Research, 2025
Invited for presentation at ICLR 2025
NeurIPS
FOCS
Semi-Bandit Learning for Monotone Stochastic Optimization
IEEE Symposium on Foundations of Computer Science, 2024
FAccT
System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes
ACM Conference on Fairness, Accountability, and Transparency, 2024
ALT
Online Recommendations for Agents with Discounted Adaptive Preferences
International Conference on Algorithmic Learning Theory, 2024
SODA
Parallel Approximate Maximum Flows in Near-Linear Work and Polylogarithmic Depth
ACM-SIAM Symposium on Discrete Algorithms, 2024
NeurIPS
When Can We Track Significant Preference Shifts in Dueling Bandits?
Neural Information Processing Systems, 2023
NeurIPS
Diversified Recommendations for Agents with Adaptive Preferences
Neural Information Processing Systems, 2022
NeurIPS
NeurIPS
An Asymptotically Optimal Batched Algorithm for the Dueling Bandit Problem
Neural Information Processing Systems, 2022
COLT
A Sharp Memory-Regret Trade-Off for Multi-Pass Streaming Bandits
Conference on Learning Theory, 2022
ICML
Batched Dueling Bandits
International Conference on Machine Learning, 2022
Long presentation (top 2%)
AISTATS
PAC Top-k Identification under SST in Limited Rounds
International Conference on Artificial Intelligence and Statistics, 2022
ALT
Stochastic Dueling Bandits with Adversarial Corruption
International Conference on Algorithmic Learning Theory, 2021
NeurIPS
ICML
Rank Aggregation from Pairwise Comparisons in the Presence of Adversarial Corruptions
International Conference on Machine Learning, 2020
ACM TEAC
SODA
ICML
COLT
Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
Conference on Learning Theory, 2017
EC
EC
COLT
On Consistent Surrogate Risk Minimization and Property Elicitation
Conference on Learning Theory, 2015
ICML
GEV-Canonical Regression for Accurate Binary Class Probability Estimation when One Class is Rare
International Conference on Machine Learning, 2014