Thibaut Horel

32 Vassar Street
Room 32-D708
Cambridge, MA 02139

I am currently a research scientist at MIT's LIDS working in Munther Dahleh's research group. I am broadly interested in algorithmic economics, computational statistics, and opti­mization.

I completed my PhD in Computer Science at Harvard University in 2019, advised by Edoardo Airoldi and David Parkes. I received my M.S. in Computer Science from ENS Paris in 2011, and my M.S. in Probability and Statistics from Université Paris-Sud in 2010. In the past, I have also interned at Technicolor Research, Yahoo! Research and Facebook Research.

Working papers

• Coordination via Selling Information [arXiv]
  Alessandro Bonatti, Munther Dahleh, Thibaut Horel, and Amir Nouripour
• Towards Data Auctions with Externalities [arXiv]
  Anish Agarwal, Munther Dahleh, Thibaut Horel, and Maryann Rui
  In submission.
• Detecting the Network Spread of Police Shooting in the Chicago Police Department [ssrn]
  Thibaut Horel, Lorenzo Masoero, Raj Agrawal, Trevor Campbell, and Daria Roithmayr
  In submission.

Publications

• Selling Information in Competitive Environments [arXiv][doi]
  Alessandro Bonatti, Munther Dahleh, Thibaut Horel, and Amir Nouripour
  In Journal of Economic Theory, 2024.
• Estimation of Models with Limited Data by Leveraging Shared Structure [arXiv][doi]
  Maryann Rui, Thibaut Horel, and Munther Dahleh
  In the 62nd IEEE Conference on Decision and Control (CDC 2023).
• Information Asymmetry and Contract Design with Applications to Agriculture [doi]
  Alessandro Bonatti, Munther Dahleh, Thibaut Horel, and Mardavij Roozbehani
  In the 62nd IEEE Conference on Decision and Control (CDC 2023).
• Entropic Compressibility of Lévy Processes [arXiv][doi]
  Julien Fageot, Alireza Fallah, and Thibaut Horel
  In IEEE Transactions on Information Theory, 2022.
• The CPD Data Set: Personnel, Use of Force, and Complaints in the Chicago Police Department [pdf]
  Thibaut Horel, Lorenzo Masoero, Raj Agrawal, Daria Roithmayr, and Trevor Campbell
  In NeurIPS 2021, Datasets and Benchmarks track.
• Optimal Bounds between f-Divergences and Integral Probability Metrics [arXiv]
  Rohit Agrawal and Thibaut Horel
  In Journal of Machine Learning Research, 2021.
  An extended abstract previously appeared in ICML 2020.
• The Proximal Robbins–Monro Method [arXiv]
  Panos Toulis, Thibaut Horel, and Edoardo M. Airoldi
  In Journal of the Royal Statistical Society (Series B), 2020.
• Data Structures Meet Cryptography: 3SUM with Preprocessing [pdf][arXiv]
  Alexander Golovnev, Siyao Guo, Thibaut Horel, Sunoo Park, and Vinod Vaikuntanathan
  In the 52nd ACM Symposium on the Theory of Computing (STOC 2020).
• Unifying Computational Entropies via Kullback–Leibler Divergence [pdf][arXiv][ePrint]
  Rohit Agrawal, Yi-Hsiu Chen, Thibaut Horel, and Salil Vadhan
  In the 39th Annual International Cryptology Conference (CRYPTO 2019).
• How to Subvert Backdoored Encryption: Security Against Adversaries that Decrypt All Ciphertexts [arXiv][ePrint]
  Thibaut Horel, Sunoo Park, Silas Richelson, and Vinod Vaikuntanathan
  In the 10th Innovations in Theoretical Computer Science Conference (ITCS 2019).
• Modeling Contagion Through Social Networks to Explain and Predict Gunshot Violence in Chicago, 2006 to 2014 [pdf][supp][doi]
  Ben Green, Thibaut Horel, and Andrew Papachristos
  In JAMA Internal Medicine, January 3 2017.
• Maximization of Approximately Submodular Functions [pdf]
  Thibaut Horel and Yaron Singer
  In Advances in Neural Information Processing Systems 29 (NeurIPS 2016).
• Inferring Graphs from Cascades: A Sparse Recovery Framework [pdf][arXiv]
  Jean Pouget-Abadie and Thibaut Horel
  In Proc. of the 32nd International Conference on Machine Learning (ICML 2015).
• Scalable Methods for Adaptively Seeding a Social Network [pdf][arXiv]
  Thibaut Horel and Yaron Singer.
  In Proc. of the 24th International World Wide Web Conference (WWW 2015).
• Budget Feasible Mechanisms for Experimental Design [pdf][arXiv]
  Thibaut Horel, Stratis Ioannidis, and Muthu Muthukrishnan
  In Proc. of the 11th Latin American Theoretical Informatics Symposium (LATIN 2014).

Teaching

• Spring 2016: TF for AM221: Advanced Optimization.
• Spring 2014: TF for AM221: Advanced Optimization.

Miscellaneous

How to pronounce my name? It is actually very simple: Thi as in tea and baut as in born (IPA: /ˈtiːbɔː/).