Elisa Celis

I am an assistant professor in the Statistics & Data Science department at Yale University. I study the manifestation of social and economic biases in our online lives via the algorithms that encode and perpetuate them. My research leverages both experimental and theoretical approaches, and my work spans multiple disciplines including data science, machine learning, fairness in socio-technical systems and algorithm design.

At Yale I co-founded the Computation and Society Initiative. I am a member of the Scholar’s Council of UCLA’s Center for Critical Internet Inquiry, an affiliated faculty of  Yale’s Institution for Social and Policy Studies and Cowles Foundation for Research in Economics, and an Advisory Board Member of the A+ Alliance.

See here for my full CV.

SELECTED NEWS:

• NSF CAREER Award, 2021
• Yale FAS Senate and Co-chair FASS Diversity Committee, 2021-
• More Competitive Search Through Regulation, Policy Discussion Paper, 2021
• ACM FAccT (formerly FAT*) Executive Committee, 2021-
• J.P. Morgan Faculty Research Award, 2020
• Named one of the 100 Brilliant Women in AI Ethics, 2020
• ACM FAT* 2020 PC Co-Chair
• LatinX in AI @ ICML 2019 Executive Chair
• Women in Big Data 2019 General Co-Chair
• Best Paper at FAT* 2019
• Taught Data Science Ethics in Spring 2019 and 2021 at Yale, see some excerpts by students on our course blog!

SELECTED PRESS & OUTREACH:

• Podcast: The Good, the Bad, and Ugly of Artificial Intelligence, 2021
• ISPS Democracy Series: Rethinking Political Representations, 2021
• Screening and discussion on CODED BIAS, 2021
• Affirmative Action Algorithms Webinar, 2021
• A Conversation with Safiya Noble, 2020
• Conversation with the Tilde Cafe on Fighting Discrimination in Artificial Intelligence, 2020
• Interview on Top of Mind with Julie Rose, 2020
• Mechanism Design for Social Good (MD4SG) Colloquium, 2019
• TEDx talk on “Should you trust what AI says?”, 2019
• Media coverage of my work on fair elections in Switzerland: [Canal 9], [Le Temps], [Le Nouvelliste],[radio], [video], 2018
• Video shorts on algorithmic bias: [video1], [video2], [video3], 2018
• Media coverage of my work on controlling polarization: [PBS Nova, 2019], [Phys.org, 2018]

SELECTED RECENT PUBLICATIONS:
(See here for my  full list of publications. For papers, demos, code, etc. related to my work on fairness, please visit Controlling bias in AI.)

• Auditing for Diversity using Representative Examples
  Vijay Keswani, L. Elisa Celis
  ACM Special Interest Group on Knowledge Discovery and Data Mining (KDD), 2021
• Data Preprocessing to Mitigate Bias: A Maximum Entropy-based Approach
  L. Elisa Celis, Vijay Keswani, Nisheeth K. Vishnoi
  International Conference on Machine Learning (ICML), 2020 [blogpost]
• Implicit Diversity in Image Summarization
  L. Elisa Celis, Vijay Keswani
  Computer-Supported Cooperative Work and Social Computing (CSCW), 2020
• Assessing Social and Intersectional Biases in Contextualized Word Representations
  Yi Chern Tan and L. Elisa Celis
  Advances in Neural Information Processing Systems (NeurIPS), 2019
• Toward Controlling Discrimination in Online Advertising
  L. Elisa Celis, Anay Mehrotra and Nisheeth Vishnoi
  International Conference on Machine Learning (ICML), 2019
  Oral presentation and Best Student Paper at Mechanism Design for Social Good (MD4SG), 2019
• Controlling Polarization in Personalization: An Algorithmic Framework
  L. Elisa Celis, Sayash Kapoor, Farnood Salehi and Nisheeth K. Vishnoi
  Best Paper Award
  Fairness Accountability and Transparency Conference (FAT*), 2019
• Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
  L. Elisa Celis, Lingxiao Huang, Vijay Keswani and Nisheeth K. Vishnoi
  Fairness Accountability and Transparency Conference (FAT*), 2019
• Coordinate Descent with Bandit Sampling
  Farnood Salehi, Patrick Thiran and L. Elisa Celis
  Advances in Neural Information Processing Systems (NeurIPS), 2018
• Ranking with Fairness Constraints
  L. Elisa Celis, Damian Straszak and Nisheeth K. Vishnoi
  International Colloquium on Automata, Languages, and Programming (ICALP), 2018