Publications
*stands for equal contribution.
Manuscipts and Preprints
Unrealized Expectations: Comparing AI Methods vs Classical Algorithms for Maximum Independent Set
Yikai Wu*, Haoyu Zhao*, Sanjeev AroraFedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning
Haoyu Zhao, Zhize Li, Peter RichtárikMildly Overparametrized Neural Nets can Memorize Training Data Efficiently
Rong Ge, Runzhe Wang, Haoyu Zhao (alpha-beta)Conference and Journal Papers
Can Models Learn Skill Composition from Examples?
Haoyu Zhao, Simran Kaur, Dingli Yu, Anirudh Goyal, Sanjeev Arora Conference on Neural Information Processing Systems ( NeurIPS 2024 )
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Kaifeng Lyu*, Haoyu Zhao*, Xingran Gu*, Dingli Yu, Anirudh Goyal, Sanjeev Arora Conference on Neural Information Processing Systems ( NeurIPS 2024 )
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao (alpha-beta) International Conference on Machine Learning ( ICML 2024 )
Do Transformers Parse while Predicting the Masked Word?
Haoyu Zhao*, Abhishek Panigrahi*, Rong Ge, Sanjeev Arora Conference on Empirical Methods in Natural Language Processing ( EMNLP 2023 )
Faster Rates for Compressed Federated Learning with Client-Variance Reduction
Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtárik SIAM Journal on Mathematics of Data Science ( SIMODS )
Task-Specific Skill Localization in Fine-tuned Language Models
Abhishek Panigrahi*, Nikunj Saunshi*, Haoyu Zhao, Sanjeev Arora International Conference on Machine Learning ( ICML 2023 )
Coresets for Vertical Federated Learning: Regularized Linear Regression and K-Means Clustering
Lingxiao Huang, Zhize Li, Jialin Sun, Haoyu Zhao (alpha-beta) Conference on Neural Information Processing Systems ( NeurIPS 2022 )
SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression
Zhize Li, Haoyu Zhao, Boyue Li, Yuejie Chi Conference on Neural Information Processing Systems ( NeurIPS 2022 )
BEER: Fast O(1/T) Rate for Decentralized Nonconvex Optimization with Communication Compression
Haoyu Zhao, Boyue Li, Zhize Li, Peter Richtárik, Yuejie Chi Conference on Neural Information Processing Systems ( NeurIPS 2022 )
Combinatorial Semi-Bandit in the Non-Stationary Environment
Wei Chen, Liwei Wang, Haoyu Zhao, Kai Zheng (alpha-beta) The Conference on Uncertainty in Artificial Intelligence ( UAI 2021 )
Combinatorial Pure Exploration of Dueling Bandit
Wei Chen, Yihan Du, Longbo Huang, Haoyu Zhao (alpha-beta) International Conference on Machine Learning ( ICML 2020 )
Online Second Price Auction with Semi-bandit Feedback Under the Non-Stationary Setting
Haoyu Zhao, Wei Chen AAAI Conference on Artificial Intelligence ( AAAI 2020 )
Gradient Method for Continuous Influence Maximization with Budget-Saving Considerations
Wei Chen, Weizhong Zhang, Haoyu Zhao (alpha-beta) AAAI Conference on Artificial Intelligence ( AAAI 2020 )
Stochastic One-Sided Full-Information Bandit
Haoyu Zhao, Wei Chen The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ( ECML/PKDD 2019 )
An FPTAS for Stochastic Unbounded Min-Knapsack Problem
Zhihao Jiang, Haoyu Zhao (alpha-beta) International Frontiers of Algorithmics Workshop ( FAW 2019 )