Selected Talks

Are the Marginal Likelihood and PAC-Bayes Bounds the Right Proxies for Generalization?

• Harvard University, Data to Actionable Knowledge Lab
• MIT, CSAIL Seminar
• CMU, Artificial Intelligence Seminar Series
• FAIR, Meta AI NYC
• Rising Stars in Machine Learning Workshop, UMD
• NeurIPS North Africans in ML Workshop, Keynote Talk

Understanding Generalization in Large Language Models through the Lens of Compression

• NeurIPS Machine Learning and Compression Workshop, Keynote Talk (upcoming)

Non-Vacuous Generalization Bounds for Large Language Models

• Cohere For AI, Guest Talk
• ML Collective, Deep Learning: Classics and Trends
• UIUC, ML Seminar

Bayesian Model Selection, the Marginal Likelihood, and Generalization

• ICML, Long Oral
• Amazon, Forecast Science Talks
• INRIA Social Data Group
• Morocco AI, Webinar Series
• ML Collective, Deep Learning: Classics and Trends

Robustness of Deep Learning Models to Distribution Shift

• ICML Women in Machine Learning Workshop, Session Co-Leader

Adaptive First and Second Order Algorithms for Large-Scale Machine Learning

• SIAM Conference on Optimization
• NeurIPS Optimization for ML Workshop, Spotlight Presentation
• Montreal Machine Learning and Optimization Group