University of Cambridge > Talks.cam > Machine Learning @ CUED > Robust Deep Learning Under Distribution Shift

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Robust Deep Learning Under Distribution Shift

Download to your calendar using vCal

If you have a question about this talk, please contact Adrian Weller .

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. However, ML systems, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to fail silently. Faced with distribution shift, we wish (i) to detect and (ii) to quantify the shift, and (iii) to correct our classifiers on the fly—when possible. This talk will describe a line of recent work on tackling distribution shift. First, I will focus on recent work on label shift, a more classic problem, where strong assumptions enable principled methods. Then I will discuss how recent tools from generative adversarial networks have been appropriated (and misappropriated) to tackle dataset shift—characterizing and (partially) repairing a foundational flaw in the method. Finally, I will discuss new work that leverages human-in-the-loop feedback to develop classifiers that take into account causal structure in text classification problem and appear (empirically) to benefit on a battery of out-of-domain evaluations.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

News Seminar Room, Herchel Smith Building, Forvie Site, Robinson Way, Cambridge CB2 0SR Average on weekdays: 9004.18006431 kWh

Other talks

Decoding genomic chaos - a pancancer compendium of chromosomal instability Thelocactus Online Causal Inference Seminar Angular analyses of b -> s ee decays at LHCb Title tbc Title abstract tbc
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity