The Journey, not the Destination: How Data Guides Diffusion Models

Speaker: Josh Vendrow , CSAIL MIT

Date: Tuesday, November 07, 2023

Time: 5:00 PM to 5:30 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Room 32-G882 (Hewlett Room)

Event Type: Seminar

Room Description:

Host: Sharut Gupta, CSAIL MIT

Contact: Sharut Gupta, sharut@mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: mitml@mit.edu, lids-seminars@mit.edu, seminars@csail.mit.edu

Reminder Subject: TALK: The Journey, not the Destination: How Data Guides Diffusion Models

Abstract: Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. However, attributing these images back to the training data—that is, identifying specific training examples which caused an image to be generated—remains a challenge. In this paper, we propose a framework that: (i) provides a formal notion of data attribution in the context of diffusion models, and (ii) allows us to counterfactually validate such attributions. Then, we provide a method for computing such attributions efficiently by leveraging recent work on data attribution in the supervised setting. Finally, we apply our method to find (and evaluate) such attributions for diffusion models trained on CIFAR-10 and MS COCO.

Speaker bio: Josh is a second year PhD student working with Aleksander Madry. Josh's research focuses on building machine learning models that are safe and robust when deployed in the real world.

Research Areas:

Impact Areas:

See other events that are part of the ML Tea.

Created by Sharut Gupta Email at Monday, November 06, 2023 at 5:48 PM.