Stanford WTF

Women in Theory Forum

Welcome to the Stanford Women in Theory Forum (WTF).  We are group of women-identifying CS-theorist-identifying (and theory-adjacent) folks who meet monthly-ish for socializing, snacks, and a research talk.  If you'd like to join our mailing list, please email the organizers, or sign up here:

Organizers: Tselil Schramm (tselil-at-stanford-dot-edu) and Mary Wootters (marykw-at-stanford-dot-edu)


AY 2022-2023

If the weather is nice, we will meet outside in the engineering quad (in the treepit with the whiteboards).  If the weather is not so nice, we'll meet inside, probably Gates 415.  Join the mailing list for announcements about locations.

Unfortunately, the standard measure of predictor quality, overall classification error, may fail to address these concerns beyond a guarantee of overall accuracy. In this talk, I will provide an overview of Outcome Indistinguishability, a recent learning paradigm introduced by Dwork, Kim, Reingold, Rothblum, and Yona that allows for more flexible tools for reasoning about the quality of predictors beyond their overall accuracy. I will also explore recent results on the sample complexity of this new learning task. 

Based on joint work with Lunjia Hu and Omer Reingold (,

In this talk, we focus on clustering and embedding graphs sampled from high-dimensional Gaussian mixture block models, where the dimension of the latent feature vectors goes to infinity as the size of the network goes to infinity. This high-dimensional setting is most appropriate in the context of modern networks, in which we think of the latent feature space as being high-dimensional. We analyze the performance of canonical spectral clustering and embedding algorithms for such graphs in the case of 2-component spherical Gaussian mixtures and begin to sketch out the information-computation landscape for clustering and embedding in these models.

This is based on joint work with Tselil Schramm.

AY 2021-2022

The schedule has been lost to time.