LIDS & Stats Tea

Tea talks are 20 minute long informal chalk-talks for the purpose of sharing ideas and making others aware about some of the topics that may be of interest to the LIDS and Stats audience. If you are interested in presenting in the upcoming seminars, please email lids_stats_tea[at]mit[dot]edu

October 4, 2023

Learning threshold neurons via the Edge of Stability, and Sharpness Aware Minimization

Kwangjun Ahn (LIDS)

n this talk, I'll be talking about interesting phenomena arising in Deep Learning optimization. In particular, based on a simple yet canonical model, we will discuss how the neural networks learn the "correct" classifiers. Surprisingly,...

October 24, 2023

Resilience of Electric Vehicle Charging in Cold Climate

Guangchun (Grant) Ruan (LIDS)

The performance and service life of electric vehicle (EV) batteries degrade deadly in cold climate, and heating is a common-but-expensive option to survive EVs in this case. Coordinating the heating and charging demand at scale has great potential...

October 25, 2023

Sample Complexity Bounds for Estimating Probability Divergences under Invariances

Behrooz Tahmasebi (CSAIL)

Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributions. In this work, we study...