Office: 45-501F
(5th floor of College of Computing bldg)
Email: gfarina AT mit.edu
Assistant: Katie O'Reilly
Gabriele Farina
I am interested in solid theoretical and algorithmic foundations for learning and computational decision-making under imperfect information. To achieve that, I combine and advance techniques and notions of strategicness from game theory together with modern tools from machine learning, optimization, and statistics.
I am an Assistant Professor at MIT in EECS and LIDS, additionally affiliated with the Operations Research Center (ORC). I hold the X-Window Consortium Career Development Chair. Before that, I spent a year as a Research Scientist at FAIR (Meta AI), where I worked on Cicero, a human-level AI agent combining strategic reasoning and natural language. Before that, I was a Ph.D. student in the Computer Science Department at Carnegie Mellon University, where I worked with Tuomas Sandholm. I was supported by a 2019-2020 Facebook Fellowship in the area of Economics and Computation.
Curriculum Vitae Publications TeachingSome current research interests
➊ No-Regret Learning Dynamics
Publications on this topic: [ = most representative]
ICLR 2024
|
|
AAAI 2024
|
|
AAAI 2024
|
|
NeurIPS 2023
|
|
NeurIPS 2023
|
Regret Matching$^+$: (In)Stability and Fast Convergence in Games
Spotlight paper
|
NeurIPS 2023
|
|
ICML 2023
|
|
ICLR 2023
|
|
ICLR 2023
|
|
J. ACM 2022
|
|
Science 2022
link |
|
NeurIPS 2022
|
|
NeurIPS 2022
|
|
ICML 2022
|
|
ICML 2022
|
|
STOC 2022
|
|
AAAI 2022
|
|
EC 2021
|
|
AAAI 2021
|
|
AAAI 2021
|
|
AAAI 2021
|
|
ICML 2020
|
|
NeurIPS 2019
|
|
ICML 2019
|
Regret Circuits: Composability of Regret Minimizers
[]
Long presentation
|
ICML 2019
|
|
AAAI 2019
|
|
NeurIPS 2018
|
Solving Large Sequential Games with the Excessive Gap Technique
Spotlight paper
|
➋ Correlation and Mediated Equilibria
Publications on this topic: [ = most representative]
EC 2024
|
|
ICLR 2024
|
|
NeurIPS 2023
|
|
J. ACM 2022
|
|
NeurIPS 2022
|
|
EC 2022
|
|
EC 2022
|
|
STOC 2022
|
|
NeurIPS 2020
|
|
NeurIPS 2020
|
|
AAAI 2020
|
|
NeurIPS 2019
|
➌ Team Games and Team Equilibria
Publications on this topic: [ = most representative]
EC 2024
|
|
NeurIPS 2023
|
|
ICML 2023
|
|
NeurIPS 2022
|
|
ICML 2021
|
|
NeurIPS 2018
|
➍ Human Modeling, Robustness to Mistakes, and Equilibrium Perfection
Publications on this topic: [ = most representative]
NAACL 2024
|
|
ICLR 2024
|
The Consensus Game: Language Model Generation via Equilibrium Search
Spotlight paper
Best paper award at "Robustness of Few-shot and Zero-shot Learning in Large Foundation Models" workshop (NeurIPS 2023) |
ICLR 2023
|
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
[]
Outstanding Paper Honorable Mention
Selected as “Notable-top-5%” |
Science 2022
link |
|
ICML 2022
|
|
NeurIPS 2021
|
|
AAAI 2019
|
|
NeurIPS 2018
|
|
IJCAI 2018
|
|
AAAI 2018
|
|
ICML 2017
|
|
IJCAI 2017
|
|
AAAI 2017
|