IFML Seminar
IFML Seminar: 11/07/25 - Model Self-improvement via Optimal Retraining
Abstract: Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model’s performance. While prior works have demonstrated the benefits of specific heuristic...
Upcoming Events
- November712:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for...
- November1412:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Diffusion language models (DLMs) represent a nascent but promising alternative to GPT-style autoregressive (AR) language models: as opposed to...
- November2112:15 - 1:15pm
IFML Seminar
Event DetailsAbstract: Intelligence often emerges through interaction and competition. Likewise, advanced AI algorithms often rely on competing learning objectives.…
Past Events
- October1512 - 1 pm
Foundational Research Seminar
Event DetailsWe 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
Event DetailsTraditional group fairness definitions are typically defined with respect to a specified classification of people into protected groups, despite many...
- October83 - 4 pm
ML+ X Seminar
Event DetailsAbstract: Understanding how two datasets differ can help us determine whether one dataset under-represents certain sub-populations, and provides insights…
- October112 - 1 pm
Foundational Research Seminar
Event DetailsAbstract: Recent theoretical works on over-parameterized neural nets have focused on two aspects: optimization and generalization. Many existing works that…
- September33 - 4 pm
ML+ X Seminar
Event DetailsAbstract Reinforcement learning (RL) has gained popularity in the research community as a model-free and adaptive control paradigm for the...
- August302 - 3 pm
Foundational Research Seminar
Event DetailsThe talk will cover two complexity-theoretic results from optimization. We will review work on an accelerated algorithm (à la Nesterov)...
