IFML Seminar
Robust Learning of a Single Index Model
Abstract: I will discuss recent results on learning a single neuron with ReLU and other activation functions, in the agnostic (i.e., adversarial label noise) setting, with the goal of achieving near-optimal mean square loss...
Upcoming Events
-
March2212:15 - 1 pm
IFML Seminar
Abstract: I will discuss recent results on learning a single neuron with ReLU and other activation functions, in the agnostic...
-
March2912:15 - 1 pm
IFML Seminar
Abstract: In this talk, we will delve into the dynamic and evolving landscape of generative AI, concentrating on three areas...
-
March292 - 5 pm
IFML + DMS Joint Event
SCHEDULE OF EVENTS 2:00 - Talk with James Zou (GDC 6.302) Abstract: This talk will explore how we can develop...
-
April18throughApril19
Save the Date for the 2024 Machine Learning Lab Research Symposium. Please join us for a two-day workshop celebrating the...
Past Events
-
March812:15 - 1 pm
IFML Seminar
Abstract: Lion (Evolved Sign Momentum) is an optimizer discovered through program search ( https://arxiv.org/abs/2302. 06675 ). It was shown to...
-
March112:15 - 1 pm
IFML Seminar
Abstract: Diffusion models have emerged as a powerful new approach to generative modeling. In this talk, we present the first...
-
February2312:15 - 1 pm
IFML Seminar
Abstract: The problem of parallel stochastic convex optimization (SCO) was first formalized by Nemirovski in ’94. In this problem, there...
-
February1612:15 - 1 pm
IFML Seminar
Abstract: Foundational large language models, while successful at shorter contexts, struggle to scale to longer context inputs. Preventing performance…
-
February212:15 - 1 pm
IFML Seminar
Abstract: The Gromov-Wasserstein (GW) distance quantifies dissimilarity between metric measure (mm) spaces and provides a natural correspondence…
-
January262 - 4 pm
Connecting undergraduate and graduate students with machine learning research opportunities across campus.