Bi-Weekly Seminar Series

Seminars are bi-weekly, on Thursdays at 12pm ET (more time zones) and last 90 minutes.

To receive announcements of upcoming seminars, join our mailing list or subscribe to our YouTube. To participate in Zoom, locate the registration link below (posted a few days before the seminar). If you are interested in giving a talk, contact trustworthyml@gmail.com.

FORMAT and instructions

The seminars will take place in Zoom Webinar; some may be recorded and live-streamed to YouTube.

The first hour typically follows one of these formats:

  • 40-min talk, followed by 20-min Q&A and moderated chat on the speaker's journey in ML and research process.

  • Rising Star Spotlights: Two talks of 20-25 mins each, followed by 5-10 min Q&A.

Then after a 5-min break, we reconvene for discussions with fellow participants. Our hope is that this participant-driven discussion in the second hour allows participants to meet new people working in similar research areas. Each seminar will also have a Twitter thread to continue the conversation.

By participating in the seminar, you agree to abide by the Code of Conduct. Please report any issues to trustworthyml@gmail.com.

Joining Zoom: There is a limit of 100 participants in Zoom, first-come-first-serve; registering does not guarantee you a spot. You can join Zoom by clicking the link in your registration confirmation email shortly before the seminar starts. We recommend downloading and installing Zoom in advance.

Live-stream and recording: If Zoom reaches capacity, please watch the YouTube live-stream and check Zoom again in case spots open up. If you do not wish to appear in the live-stream and recording, please only join Zoom in the second hour. You can find recordings of previous seminars here.

Participate: In Zoom, you will be muted in the first hour however you can ask questions using Zoom's Q&A tool. You can also upvote and leave comments on questions. The moderator will select questions, and may call on you to ask yours. In the second hour, you will be un-muted for a free-form discussion with fellow participants. You can use the Twitter thread to continue the conversation after the seminar.

UPCOMING SEMINARS

Click to see abstract, bio, registration link, and Twitter thread. Click here to see the recordings of the past seminars.

Mar 4, 2021 Rising Star Spotlights

Shibani Santurkar, MIT. How Do ML Models Make Decisions?

Victor Farias, Universidade Federal do Ceará, Brazil. Differential Privacy for Non-numeric Queries via Local Sensitivity

Shibani's Abstract: Machine learning models today attain impressive accuracy on many benchmark tasks. Yet, these models remain remarkably brittle---small perturbations of natural inputs can completely degrade their performance.

Why is this the case?

In this talk, we take a closer look at this brittleness, and examine how it can, in part, be attributed to the fact that our models often make decisions very differently to humans. Viewing neural networks as feature extractors, we study how these extracted features may diverge from those used by humans. We then take a closer look at the building blocks of the ML pipeline to identify potential sources of this divergence and discuss how we can make progress towards mitigating it.

Shibani's Bio: Shibani Santurkar is a PhD student in the MIT EECS Department, advised by Aleksander Mądry and Nir Shavit. Her research revolves around two broad themes: developing a precise understanding of widely-used deep learning techniques; and identifying avenues to make machine learning be robust and reliable. Prior to joining MIT, she received a bachelor's degree in electrical engineering from IIT Bombay, India. She is a recipient of the Google Fellowship.

Victor's abstract: Differential privacy is the state-of-the-art formal definition for data release under strong privacy guarantees. A variety of mechanisms have been proposed in the literature for privately releasing the noisy output of non-numeric queries (i.e., queries that produce discrete outputs) by perturbing the output of the query. Those mechanisms use the notion of global sensitivity to calibrate the amount of noise one should inject to cover the individuals’ identity. A related notion named local sensitivity has been used in many numeric queries (i.e., queries that produce numeric outputs) to reduce the noise injected however it has not been used for non-numeric queries. In this talk, we discuss how to adapt the notion of local sensitivity for non-numeric queries and present a generic approach to apply it. We illustrate the effectiveness of this approach by applying it to two diverse problems: influential node analysis and decision tree induction.

Victor's Bio: Victor is a fifth year PhD student at Universidade Federal do Ceará - Brazil advised by Prof. Javam Machado. His research interests include Differential Privacy, Machine Learning and Databases. His thesis is on applying local sensitivity on differentially private selection with applications on graph analysis and tree induction algorithms. This work has been carried out in collaboration with Divesh Srivastava at AT&T Labs Research. Victor completed a Masters in Computer Science from the department of computer Science in Universidade Federal do Ceará – Brazil where he worked on elasticity for distributed databases using machine learning with a research visit period at Télécom SudParis - France.

Zoom registration: https://us02web.zoom.us/webinar/register/WN_JjYVljUhRqOB9Oj59uA4ZA

YouTube live-stream and recording: https://youtu.be/_s-Li0I18vU

Twitter thread to continue the conversation: Check back again after the seminar.

Mar 18, 2021: Katherine Heller, Google / Duke University

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Apr 1, 2021: Gautam Kamath, University of Waterloo

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Apr 15, 2021: Suresh Venkatasubramanian, University of Utah

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Apr 29, 2021 Rising Star Spotlights

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

May 13, 2021: Alexander D'Amour, Google Brain

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

May 27, 2021: Hoda Heidari, Carnegie Mellon University

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

June 24, 2021 Rising Star Spotlights

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

July 8, 2021: Cynthia Rudin, Duke University

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

August 19, 2021 Rising Star Spotlights

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Sep 16, 2021: Sherri Rose, Stanford University

Identifying Subgroups in Algorithmic Fairness

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Sep 30, 2021: Sanmi Koyejo, University of Illinois at Urbana-Champaign

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.

Oct 14, 2021 Rising Star Spotlights

Title TBA

Abstract TBA

Zoom registration: Check back again a few days before the seminar.

YouTube live-stream and recording: Check back again a few days before the seminar.

Twitter thread to continue the conversation: Check back again after the seminar.