Research

[Publications | Preprints | Invited talks]

My academic research interests lie at the intersection of Machine Learning, Economics and Statistics, in particular designing new algorithms and building ML systems that are robust, distributed, and responsive to the evolving social and economic needs.

Papers by Topics: [show publications by date]

Machine learning and Economics, Game Theory

Mechanisms that Incentivize Data Sharing in Federated Learning [PDF]
with Sai Praneeth Karimireddy and Michael I. Jordan
No-Regret Learning in Partially-Informed Auctions [PDF]
Wenshuo Guo, Michael I. Jordan and Ellen Vitercik (alphabetical order)

ICML 2022 ‣ 39th International Conference on Machine Learning
Robust Learning of Optimal Auctions [PDF]
Wenshuo Guo, Michael I. Jordan and Manolis Zampetakis (alphabetical order)

NeurIPS 2021 ‣ 35th Conference on Neural Information Processing Systems Spotlight (top 3% submissions)
A Variational Inequality Approach to Bayesian Regression Games [PDF]
Wenshuo Guo, Michael I. Jordan and Tianyi Lin (alphabetical order)

CDC 2021 ‣ 60th IEEE Conference on Decision and Control
Finding Equilibrium in Multi-Agent Games with Payoff Uncertainty [PDF | slides | video]
Wenshuo Guo, Mihaela Curmei, Serena Wang, Benjamin Recht and Michael I. Jordan

ICML 2020 ‣ Workshop on Theoretical Foundations of Reinforcement Learning

Online Learning and Bandits

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws [PDF]
with Kush Bhatia and Jacob Steinhardt

AISTATS 2023 ‣ 26th International Conference on Artificial Intelligence and Statistics
No-Regret Learning in Partially-Informed Auctions [PDF]
Wenshuo Guo, Michael I. Jordan and Ellen Vitercik (alphabetical order)

ICML 2022 ‣ 39th International Conference on Machine Learning
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits [PDF | code]
Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Asim Biswal, Vidya Muthukumar and Ashwin Pananjady

AISTATS 2022 ‣ 25th International Conference on Artificial Intelligence and Statistics

Preliminary version appeared at ICML'21 Workshop on Human-AI Collaboration in Sequential Decision-Making (spotlight) and ICML'21 Workshop on Reinforcement Learning Theory
Learning Competitive Equilibria in Exchange Economies with Bandit Feedback [PDF]
Wenshuo Guo, Kirthevasan Kandasamy, Joseph E. Gonzalez, Michael I. Jordan and Ion Stoica

AISTATS 2022 ‣ 25th International Conference on Artificial Intelligence and Statistics

Causal Learning and Reasoning

Off-Policy Evaluation with Policy-Dependent Optimization Response [PDF]
Wenshuo Guo, Michael I. Jordan and Angela Zhou (alphabetical order)

NeurIPS 2022 ‣ 36th Conference on Neural Information Processing Systems
Multi-Source Causal Inference Using Control Variates [PDF]
Wenshuo Guo*, Serena Wang*, Peng Ding, Yixin Wang and Michael I. Jordan

TMLR ‣ Journal of Transactions on Machine Learning Research
Partial Identification with Noisy Covariates: A Robust Optimization Approach [PDF]
Wenshuo Guo, Mingzhang Yin, Yixin Wang and Michael I. Jordan

CLeaR 2022 ‣ 1st International Conference on Causal Learning and Reasoning

Optimal Transport, Variational Methods, Kernels

A Variational Inequality Approach to Bayesian Regression Games [PDF]
Wenshuo Guo, Michael I. Jordan and Tianyi Lin (alphabetical order)

CDC 2021 ‣ 60th IEEE Conference on Decision and Control
Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter [PDF | slides]
Wenshuo Guo, Nhat Ho and Michael I. Jordan

AISTATS 2020 ‣ 23th International Conference on Artificial Intelligence and Statistics
Neural Kernel Without Tangents [PDF | slides | video | code ]
Vaishaal Shankar, Alex Fang, Wenshuo Guo, Sara Fridovich-Keil, Ludwig Schmidt, Jonathan Ragan-Kelly Benjamin Recht

ICML 2020 ‣ 37th International Conference on Machine Learning

Collaborative Machine Learning, Fairness, Societal Impacts

Mechanisms that Incentivize Data Sharing in Federated Learning [PDF]
with Sai Praneeth Karimireddy and Michael I. Jordan
Test-time Collective Prediction [PDF]
Celestine Mendler-Dünner, Wenshuo Guo, Stephen Bates and Michael I. Jordan

NeurIPS 2021 ‣ 35th Conference on Neural Information Processing Systems
The Stereotyping Problem in Collaboratively Filtered Recommender Systems [PDF]
Wenshuo Guo*, Karl Krauth*, Nikhil Garg and Michael I. Jordan

EAAMO 2021 ‣ ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization
Robust Optimization for Fairness with Noisy Protected Groups [PDF | code]
Serena Wang*, Wenshuo Guo*, Harikrishna Narasimhan, Andrew Cotter, Maya Gupta and Michael I. Jordan

NeurIPS 2020 ‣ 34th Conference on Neural Information Processing Systems

Preliminary version appeared at 4th Workshop on Mechanism Design for Social Good
Approximate Heavily-Constrained Learning with Lagrange Multiplier Models [PDF | code]
Harikrishna Narasimhan, Andrew Cotter, Yichen Zhou, Serena Wang, Wenshuo Guo

NeurIPS 2020 ‣ 34th Conference on Neural Information Processing Systems

Multi-Tenant Systems and Applications

Cilantro: Performance-Aware Resource Allocation for General Objectives via Online Feedback [PDF]
with Romil Bhardwaj, Kirthevasan Kandasamy, Asim Biswal, Benjamin Hindman, Joseph E. Gonzalez, Michael I. Jordan and Ion Stoica

OSDI 2023 ‣ 17th USENIX Symposium on Operating Systems Design and Implementation
Do Offline Metrics Predict Online Performance in Recommender Systems? [PDF | Berkeley RecLab]
with Karl Krauth, Sarah Dean, Alex Zhao, Mihaela Curmei, Benjamin Recht and Michael I. Jordan

Preliminary version appeared at NeurIPS'21 Workshop on Consequential Decisions in Dynamic Environments

Publications: [show by topic]

Cilantro: Performance-Aware Resource Allocation for General Objectives via Online Feedback [PDF]
with Romil Bhardwaj, Kirthevasan Kandasamy, Asim Biswal, Benjamin Hindman, Joseph E. Gonzalez, Michael I. Jordan and Ion Stoica

OSDI 2023 ‣ 17th USENIX Symposium on Operating Systems Design and Implementation
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws [PDF]
with Kush Bhatia and Jacob Steinhardt

AISTATS 2023 ‣ 26th International Conference on Artificial Intelligence and Statistics
Multi-Source Causal Inference Using Control Variates [PDF]
Wenshuo Guo*, Serena Wang*, Peng Ding, Yixin Wang and Michael I. Jordan

TMLR ‣ Journal of Transactions on Machine Learning Research
Off-Policy Evaluation with Policy-Dependent Optimization Response [PDF]
Wenshuo Guo, Michael I. Jordan and Angela Zhou (alphabetical order)

NeurIPS 2022 ‣ 36th Conference on Neural Information Processing Systems
No-Regret Learning in Partially-Informed Auctions [PDF]
Wenshuo Guo, Michael I. Jordan and Ellen Vitercik (alphabetical order)

ICML 2022 ‣ 39th International Conference on Machine Learning
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits [PDF | code]
Wenshuo Guo, Kumar Krishna Agrawal, Aditya Grover, Asim Biswal, Vidya Muthukumar and Ashwin Pananjady

AISTATS 2022 ‣ 25th International Conference on Artificial Intelligence and Statistics

Preliminary version appeared at ICML'21 Workshop on Human-AI Collaboration in Sequential Decision-Making (spotlight) and ICML'21 Workshop on Reinforcement Learning Theory
Learning Competitive Equilibria in Exchange Economies with Bandit Feedback [PDF]
Wenshuo Guo, Kirthevasan Kandasamy, Joseph E. Gonzalez, Michael I. Jordan and Ion Stoica

AISTATS 2022 ‣ 25th International Conference on Artificial Intelligence and Statistics
Partial Identification with Noisy Covariates: A Robust Optimization Approach [PDF]
Wenshuo Guo, Mingzhang Yin, Yixin Wang and Michael I. Jordan

CLeaR 2022 ‣ 1st International Conference on Causal Learning and Reasoning
Robust Learning of Optimal Auctions [PDF]
Wenshuo Guo, Michael I. Jordan and Manolis Zampetakis (alphabetical order)

NeurIPS 2021 ‣ 35th Conference on Neural Information Processing Systems Spotlight (top 3% submissions)
Test-time Collective Prediction [PDF]
Celestine Mendler-Dünner, Wenshuo Guo, Stephen Bates and Michael I. Jordan

NeurIPS 2021 ‣ 35th Conference on Neural Information Processing Systems
A Variational Inequality Approach to Bayesian Regression Games [PDF]
Wenshuo Guo, Michael I. Jordan and Tianyi Lin (alphabetical order)

CDC 2021 ‣ 60th IEEE Conference on Decision and Control
The Stereotyping Problem in Collaboratively Filtered Recommender Systems [PDF]
Wenshuo Guo*, Karl Krauth*, Nikhil Garg and Michael I. Jordan

EAAMO 2021 ‣ ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization
Finding Equilibrium in Multi-Agent Games with Payoff Uncertainty [PDF | slides | video]
Wenshuo Guo, Mihaela Curmei, Serena Wang, Benjamin Recht and Michael I. Jordan

ICML 2020 ‣ Workshop on Theoretical Foundations of Reinforcement Learning
Robust Optimization for Fairness with Noisy Protected Groups [PDF | code]
Serena Wang*, Wenshuo Guo*, Harikrishna Narasimhan, Andrew Cotter, Maya Gupta and Michael I. Jordan

NeurIPS 2020 ‣ 34th Conference on Neural Information Processing Systems

Preliminary version appeared at 4th Workshop on Mechanism Design for Social Good
Approximate Heavily-Constrained Learning with Lagrange Multiplier Models [PDF | code]
Harikrishna Narasimhan, Andrew Cotter, Yichen Zhou, Serena Wang, Wenshuo Guo

NeurIPS 2020 ‣ 34th Conference on Neural Information Processing Systems
Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter [PDF | slides]
Wenshuo Guo, Nhat Ho and Michael I. Jordan

AISTATS 2020 ‣ 23th International Conference on Artificial Intelligence and Statistics
Neural Kernel Without Tangents [PDF | slides | video | code ]
Vaishaal Shankar, Alex Fang, Wenshuo Guo, Sara Fridovich-Keil, Ludwig Schmidt, Jonathan Ragan-Kelly Benjamin Recht

ICML 2020 ‣ 37th International Conference on Machine Learning
Optimization of Financial Network Stability by Genetic Algorithm [PDF]
Juntao Wang, Wenshuo Guo and Szeto Kwok Yip

WI 2018 ‣ 18th IEEE/WIC/ACM International Conference on Web Intelligence
Minimization of Systemic Risk for Directed Network Using Genetic Algorithm [PDF]
Wenshuo Guo and Szeto Kwok Yip

Evo* 2017 ‣ International Conference on the Applications of Evolutionary Computation
Spin Model of Two Random Walkers in Complex Networks [PDF]
Wenshuo Guo and Szeto Kwok Yip

CNA 2017 ‣ 6th International Conference on Complex Networks and Their Applications

Preprints:

Mechanisms that Incentivize Data Sharing in Federated Learning [PDF]
with Sai Praneeth Karimireddy and Michael I. Jordan
Do Offline Metrics Predict Online Performance in Recommender Systems? [PDF | Berkeley RecLab]
with Karl Krauth, Sarah Dean, Alex Zhao, Mihaela Curmei, Benjamin Recht and Michael I. Jordan

Preliminary version appeared at NeurIPS'21 Workshop on Consequential Decisions in Dynamic Environments

Invited Talks:

" Application-Driven Incentive-Aware Algorithm Design"
at Workshop in Operations Research and Data Science (WORDS'22), Duke University, November 2022
"Algorithm Design for Social and Economic Needs"
at Rising Stars in Machine Learning, University of Maryland, November 2022
"Application-Driven Incentive-Aware Algorithm Design"
at Rising Stars in EECS Workshop, UT Austin, October 2022
"Towards Credible Data-Driven Decision-Making under Social and Economic Needs"
at Google Brain, May 2022
"No-Regret Learning in Partially-Informed Auctions"
at NYU Stern Operations Management group, February 2022
"Machine Learning meets Economics: Learning under Social and Economic Needs"
at Morgan Stanley machine learning research, January 2022
"Towards Adaptive and Robust Learning in Data-Driven Mechanism Design"
at UC Berkeley BAIR/CPAR/BDD seminar hosted by the Berkeley Artificial Intelligence Research Lab, in conjunction with CITRIS People & Robots and Berkeley DeepDrive, September 2021
"Robust Learning of Optimal Auctions"
at 2021 Google PhD Fellowship Summit, August 2021
"Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits"
at ICML'21 Workshop on Human-AI Collaboration in Sequential Decision-Making, July 2021