
IFML Seminar
IFML Seminar: 10/24/25 - Learning from Many Trajectories
Abstract: Learning from sequential, temporally-correlated data is a core facet of modern machine learning and statistical modeling. Yet our fundamental understanding of sequential learning remains incomplete, particularly in the multi-trajectory setting where data consists...
Upcoming Events
- October2412:15 - 1:15pm
IFML Seminar
Abstract: Learning from sequential, temporally-correlated data is a core facet of modern machine learning and statistical modeling. Yet our fundamental...
- November712:15 - 1:15pm
IFML Seminar
Abstract: Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for...
Past Events
- November1912 - 1 pm
Abstract: fastMRI is a collaboration project between Facebook AI Research and the NYU School of Medicine with the goal of...
- November123 - 4 pm
ML+ X Seminar
The recent artificial intelligence (AI) boom has been primarily driven by three confluence forces: algorithms, big-data, and computing power enabled...
- November2throughNovember5
Workshop
Members of the new NSF AI Institute for Foundations of Machine Learning (IFML) will spend a week in residence at...
- October223 - 4 pm
ML+ X Seminar
Natural language contains information that must be integrated over multiple timescales. To understand how the human brain represents this information...
- October1512 - 1 pm
Foundational Research Seminar
We consider the problem of quantifying uncertainty for the estimation error of the leading eigenvector from Oja's algorithm for streaming...
- October112 - 3 pm
Ethics/Fairness in AI Seminar
Traditional group fairness definitions are typically defined with respect to a specified classification of people into protected groups, despite many...