IFML Seminar
IFML Seminar: 03/13/26 - Foundations of Reliable Learning with Imperfect Data
Abstract: A central challenge in machine learning is reliability: ensuring that an algorithm’s predictions remain accurate and stable even when the data is noisy, adversarial, or misspecified. This talk presents recent progress on learning...
Upcoming Events
- March1312:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: A central challenge in machine learning is reliability: ensuring that an algorithm’s predictions remain accurate and stable even when...
Past Events
- November1712:15 - 1 pm
IFML Seminar
Event DetailsAbstract: In this talk, we will present a recent result that if a Boolean function exhibits a sharp threshold at...
- November312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Distribution matching (DM) has emerged as a cornerstone of trustworthy machine learning, finding application in fairness, robustness, causality,…
- October2012:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Modern city governance relies heavily on crowdsourcing to identify problems such as downed trees and power-lines. Two major concerns...
- October612:15 - 1 pm
IFML Seminar
Event DetailsAbstract: During this presentation, I will delve into an innovative class of optimization problems called finite-sum coupled compositional optimization (FCCO…
- September2912:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Datasets used in machine learning and statistics are huge and often imperfect, e.g., they contain corrupted data, examples with...
- September2212:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Graph neural networks (GNNs) are successful at learning representations from most types of network data but suffer from limitations...
