Sign in

Andrew Ilyas

@aifi.bsky.social
240 followers 88 following 10 posts

Machine Learning | Stein Fellow @ Stanford Stats (current) | Assistant Prof @ CMU (incoming) | PhD @ MIT (prev) andrewilyas.com

PostsRepliesMedia
Reposted by Andrew Ilyas
Felix Zhou @felix-zhou-cfz.bsky.social · 19/04/2025
"What makes a good fisherman as opposed to other professions?" This question can be formulated as a k-linear regression problem with self-selection bias. Alkis, @anaymehrotra.bsky.social, and I design faster local convergence algorithms for this problem: arxiv.org/abs/2504.07133 (1/7)
arxiv.org
Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases and Beyond
We revisit the problem of estimating $k$ linear regressors with self-selection bias in $d$ dimensions with the maximum selection criterion, as introduced by Cherapanamjeri, Daskalakis, Ilyas, and Zamp...
152
Andrew Ilyas @aifi.bsky.social · 10/04/2025
Had a great time @simonsinstitute.bsky.social last week talking about new & upcoming work on meta-optimization of ML training tl;dr: we show how to compute gradients *through* the training process & use them to optimize training. Immediate big gains on data selection, poisoning, attribution & more!
191
Reposted by Andrew Ilyas
Elisa Nguyen @elinguyen.bsky.social · 20/01/2025
We'd love to hear your feedback if you attended the ATTRIB workshop at @neuripsconf.bsky.social 2024! Please consider taking 2-3 min to fill out this anonymous form: forms.gle/JzGebsx9haD5... Thank you!🙏
forms.gle
ATTRIB 2024 Feedback
If you attended the ATTRIB workshop at NeurIPS 2024, please consider filling out this survey. We value your feedback and would love to hear about your experience. This short survey will take just 2–...
061
Andrew Ilyas @aifi.bsky.social · 14/12/2024
Our first talk of the day @ ATTRIB 2024 (Rm 205-207): @surbhigoel.bsky.social on attributing model behavior using synthetic data!
151
Reposted by Andrew Ilyas
Seong Joon Oh @coallaoh.bsky.social · 14/12/2024
Giving a talk tomorrow at #NeurIPS2024 on the exciting topic of explainability!
0111
Andrew Ilyas @aifi.bsky.social · 14/12/2024
At NeurIPS? Come by the 2nd workshop on Attributing Model Behavior at Scale (ATTRIB)! Meeting Rm 205-207 @ 9am - amazing talks by @surbhigoel.bsky.social @sanmikoyejo.bsky.social Baharan Mirzasoleiman, Robert Geirhos, @coallaoh.bsky.social + exciting contributed talks! Details: attrib-workshop.cc
attrib-workshop.cc
ATTRIB 2024 WorkshopConference Schedule
060
Reposted by Andrew Ilyas
Monica Agrawal @monicaagrawal.bsky.social · 18/11/2024
I am recruiting PhD students at Duke! Please apply to Duke CS or CBB if you are interested in developing new methods and paradigms for NLP/LLMs in healthcare. For details, see here: monicaagrawal.com/home/researc....
0146
Reposted by Andrew Ilyas
Nikhil Garg @nkgarg.bsky.social · 19/11/2024
Primarily written for the Operations market, but folks may find this guide I wrote for the job market: gargnikhil.com/files/Nikhil...
gargnikhil.com
1215