MINDS & CIS Fall Seminar Series: Yoav Wald, “Towards Invariant Learning”
Abstract: Modern machine learning models seem to be improving on a daily basis, but still fail to generalize on out-of-distribution (OOD) data. To overcome this challenge, many techniques have been proposed, often focused on learning models with certain invariance properties. Unfortunately, so far these attempts have had limited success scaling to realistic high-dimensional data, and in learning truly invariant representations. The main part of the talk will cover work that proposes an alternative and relatively simple approach, drawing a link between OOD performance and model calibration. We argue that calibration across multiple domains can be viewed as a type of invariance that helps discard spurious correlations, hence leading to better OOD generalization. This leads us to propose multi-domain calibration as a measurable and trainable surrogate for the OOD performance of a classifier. Building on our theoretical and empirical findings, the rest of the talk will cover ongoing and recently completed research on aspects of invariant learning.
Biography: Yoav is a postdoctoral fellow at Johns Hopkins’ Whiting School of Engineering, working on safe and robust machine learning with applications in Healthcare. He completed his PhD at the Hebrew University of Jerusalem, where he was advised by Amir Globerson. During his PhD Yoav was also a researcher at Google Research, where he built methods for explaining computer vision models. He co-organized the workshop on Spurious Correlations, Invariance and Stability (SCIS) in ICML 2022.
In-person at Clark 110 & over Zoom
Join Zoom Meeting
https://wse.zoom.us/j/98624413365
Meeting ID: 986 2441 3365
One tap mobile
+13017158592,,98624413365# US (Washington DC)
+16469313860,,98624413365# US
Dial by your location
+1 301 715 8592 US (Washington DC)
+1 646 931 3860 US
+1 309 205 3325 US
+1 312 626 6799 US (Chicago)
+1 646 558 8656 US (New York)
+1 669 900 6833 US (San Jose)
+1 719 359 4580 US
+1 253 215 8782 US (Tacoma)
+1 346 248 7799 US (Houston)
+1 386 347 5053 US
+1 564 217 2000 US
+1 669 444 9171 US
Meeting ID: 986 2441 3365
Find your local number: https://wse.zoom.us/u/asoOElnUp
Join by SIP
Join by H.323
162.255.37.11 (US West)
162.255.36.11 (US East)
115.114.131.7 (India Mumbai)
115.114.115.7 (India Hyderabad)
213.19.144.110 (Amsterdam Netherlands)
213.244.140.110 (Germany)
103.122.166.55 (Australia Sydney)
103.122.167.55 (Australia Melbourne)
149.137.40.110 (Singapore)
64.211.144.160 (Brazil)
149.137.68.253 (Mexico)
69.174.57.160 (Canada Toronto)
65.39.152.160 (Canada Vancouver)
207.226.132.110 (Japan Tokyo)
149.137.24.110 (Japan Osaka)
Meeting ID: 986 2441 3365