
IFML Seminar
IFML Seminar: 05/02/25 - A New Paradigm for Learning with Distribution Shift
Abstract: We revisit the fundamental problem of learning with distribution shift, where a learner is given labeled samples from training distribution D, unlabeled samples from test distribution D′ and is asked to output a...
Upcoming Events
- May212:15 - 1:15pm
IFML Seminar
Abstract: We revisit the fundamental problem of learning with distribution shift, where a learner is given labeled samples from training...
Past Events
- April2512:15 - 1:15pm
IFML Seminar
Abstract : In the literature on benign overfitting in linear models, also referred to as minimum norm interpolation, it is...
- April1812:15 - 1:15pm
IFML Seminar
Abstract: Ill-posed inverse problems appear in many critical scientific imaging scenarios where the goal is to reconstruct cleaner images faster...
- April1112:15 - 1:15pm
IFML Seminar
Abstract: The widespread deployment of AI systems in critical domains demands more rigorous approaches to evaluating their capabilities and safety...
- April412:15 - 1:15pm
IFML Seminar
Abstract: Self-play has powered breakthroughs in two-player and multiplayer games. In this talk, I show that self-play is a surprisingly...
- March2812:15 - 1:15pm
IFML Seminar
Abstract: In this talk, we first discuss a new one-shot lower bound on the Bayes error in simple binary hypothesis...
- March1412:15 - 1:15pm
IFML Seminar
Abstract: Diffusion-based generative models transform random noise into images; their inversion aims to transform images back to structured noise that...