Publications by Tuomas Sandholm

Preprint

Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games

2022
Anagnostides I, Farina G, Panageas I, Sandholm T

Conference

Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games

2022 • Advances in Neural Information Processing Systems
Zhang BH, Sandholm T

Preprint

Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games

2022
Zhang BH, Sandholm T

Preprint

Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games

2022
McAleer S, Lanier J, Wang K, Baldi P, Fox R, Sandholm T

Conference

Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts

2022 • Advances in Neural Information Processing Systems
Balcan M-F, Prasad S, Sandholm T, Vitercik E

Preprint

Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts

2022
Balcan M-F, Prasad S, Sandholm T, Vitercik E

Conference

Subgame Solving in Adversarial Team Games

2022 • Advances in Neural Information Processing Systems
Zhang BH, Carminati L, Cacciamani F, Farina G, Olivieri P, Gatti N, Sandholm T

Preprint

2022
Zhang BH, Sandholm T

Journal Article

2022 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 5252-5259
Zhang BH, Sandholm T

Preprint

Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games

2022
Anagnostides I, Farina G, Kroer C, Lee C-W, Luo H, Sandholm T

Conference

Uncoupled Learning Dynamics with <i>O</i>(log T) Swap Regret in Multiplayer Games

2022 • Advances in Neural Information Processing Systems
Anagnostides I, Farina G, Kroer C, Lee C-W, Luo H, Sandholm T

Conference

Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games

2021 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 35:5372-5380
Farina G, Schmucker R, Sandholm T

Preprint

Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games

2021
Farina G, Schmucker R, Sandholm T

Conference

Better Regularization for Sequential Decision Spaces

2021 432-432
Farina G, Kroer C, Sandholm T

Preprint

Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

2021
Farina G, Kroer C, Sandholm T

Conference

Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

2021 • INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139 • 139:
Farina G, Celli A, Gatti N, Sandholm T

Preprint

Efficient Decentralized Learning Dynamics for Extensive-Form Coarse Correlated Equilibrium: No Expensive Computation of Stationary Distributions Required

2021
Farina G, Celli A, Sandholm T

Conference

Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium

2021 • Advances in Neural Information Processing Systems • 11:8845-8856
Farina G, Sandholm T

Preprint

Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games

2021
Farina G, Sandholm T

Preprint

Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent

2021
Farina G, Kroer C, Sandholm T

Preprint

Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games

2021
Zhang BH, Sandholm T

Conference

Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games

2021 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 35:5779-5788
Zhang BH, Sandholm T

Conference

Generalization in Portfolio-Based Algorithm Selection

2021 • Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence • 35:12225-12232
Balcan M-F, Sandholm T, Vitercik E

Preprint

How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design

2021
Balcan M-F, DeBlasio D, Dick T, Kingsford C, Sandholm T, Vitercik E

Conference

How much data is sufficient to learn high-performing algorithms? generalization guarantees for data-driven algorithm design

2021 • Annual ACM Symposium on Theory of Computing • 919-932
Balcan M-F, DeBlasio D, Dick T, Kingsford C, Sandholm T, Vitercik E

At a Glance

Academic Offerings

Admissions

Directory Submenu

People

Explore the Field

Publications by Tuomas Sandholm

Preprint

Conference

Preprint

Preprint

Conference

Preprint

Conference

Preprint

Journal Article

Preprint

Conference

Conference

Preprint

Conference

Preprint

Conference

Preprint

Conference

Preprint

Preprint

Preprint

Conference

Conference

Preprint

Conference

At a Glance

Academic Offerings

Admissions

Directory Submenu

People

Explore the Field

What can we help you find?

Preprint

Conference

Preprint

Preprint

Conference

Preprint

Conference

Preprint

Journal Article

Preprint

Conference

Conference

Preprint

Conference

Preprint

Conference

Preprint

Conference

Preprint

Preprint

Preprint

Conference

Conference

Preprint

Conference