Foundation Models

M Gerstgrasser, R Schaeffer, A Dey, R Rafailov, H Sleight, J Hughes, T Korbak, R Agrawal, D Pai, A Gromov, D A Roberts, D Yang, D L Donoho, S Koyejo: Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data [arXiv]

O Shaikh, K Gligorić, A Khetan, M Gerstgrasser, D Yang, D Jurafsky: Grounding Gaps in Language Model Generations. NAACL 2024. [arXiv]

Multi-Agent RL

Gerstgrasser M, T Danino, S Keren: Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning. NeurIPS 2023. [arXiv] [NeurIPS WS Deep RL] [AAMAS 2023 EA]

Gerstgrasser M, D Parkes: Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning. ICML 2023. [arXiv] [NeurIPS WS Meta-Learning] [NeurIPS WS Multi-Agent Security]

Brero G, A Eden, D Chakrabarti, M Gerstgrasser, V Li, D Parkes: Stackelberg POMDP: A Reinforcement Learning Approach for Economic Design. Under Review at AAAI 2024. [arXiv] [ICML WS]

S Keren, M Gerstgrasser, O Abu, J Rosenschein: Collaboration Promotes Group Resilience in Multi-Agent AI. [arXiv]

T Danino, M Gerstgrasser, S Keren: Collaborative DQN with Collaborative Estimations. Under review at AAAI 2024.

Gerstgrasser M, R Trivedi, D Parkes: CrowdPlay: Crowdsourcing Human Demonstrations for Offline Learning. ICLR 2022. [PDF] [Website]

Brero G, A Eden, M Gerstgrasser, D Parkes, D Rheingans-Yoo: Reinforcement Learning of Simple Indirect Mechanisms. AAAI 2021. [PDF] [arXiv]

Algorithmic Game Theory

Gerstgrasser, M: Reverse auctions are different from auctions. Information Processing Letters. 2019 147:49–54. [PDF]

Gerstgrasser M, P Goldberg, B de Keijzer, P Lazos, A Skopalik: Multi-Unit Bilateral Trade. AAAI 2019. [PDF]

Gerstgrasser M: On the complexity of optimal correlated auctions and reverse auctions. AAMAS 2018. [PDF]

Gerstgrasser M, P Goldberg, E Koutsoupias: Revenue Maximisation for Market Intermediation with Correlated Priors. SAGT 2016. [PDF]

Machine Learning

Fruehwirt W, G Dorffner, S Roberts, M Gerstgrasser, D Grossegger, R Schmidt, P Dal-Bianco, G Ransmayr, H Garn, M Waser, T Benke: Associations of event-related brain potentials and Alzheimer’s disease severity: A longitudinal study. Progress in Neuropsychopharmacology & Biological Psychiatry. 2019 92:31-38. [PDF]

Fruehwirt W, M Gerstgrasser, P Zhang, L Weydemann, M Waser, R Schmidt, T Benke, P Dal-Bianco, G Ransmayr, D Grossegger, H Garn, G W Peters, S Roberts, G Dorffner: Riemannian tangent space mapping and elastic net regularization for cost-effective EEG markers of brain atrophy in Alzheimer’s disease. arXive preprint 2017. [PDF]

Fruehwirt W, P Zhang, M Gerstgrasser, D Grossegger, R Schmidt, T Benke, P Dal-Bianco, G Ransmayr, L Weydemann, H Garn, M Waser, M Osborne, G Dorffner: Bayesian Gaussian process classification from event-related brain potentials in Alzheimer’s disease. AIME 2017. [PDF]

Gerstgrasser M, S Nicholls, M Stout, K Smart, C Powell, T Kypraios, D J Stekel: A Bayesian approach to analysing phenotype microarray data enables estimation of microbial growth parameters. Journal of Bioinformatics and Computational Biology. 2016 14(03). [PDF]