Feedback and comments welcome. Thanks to @gavinrbrown1 @ycherapanamjeri @Samuel_BKH @mahbodm_ @argymouz @zakynthinou for their comments thus far. 2/2 https://
arxiv.org/abs/2412.02670
@thegautamkamath
-
Research Paper Feedback and Acknowledgments for arXiv Submission
By
–
-
Computationally Efficient Methods for Robust Mean Estimation
By
–
I wrote a survey article on computationally efficient methods for "robust" mean estimation, which includes robustness to contamination, heavy-tailed data, or in the sense of differential privacy. The same ideas are useful for all 3 (seemingly-different) forms of robustness! 1/2
-
Canadian AI Researchers Starter Pack on Social Media
By
–
In case you've been looking for your favourite Canadian AI researchers on the other place, I made a starter pack of Canada @CIFAR_News AI Chairs! Let me know if I missed anyone.
-
Pascale Gourdeau discusses computability of robust learning
By
–
The last talk of the day, prior to some breakout sessions, is by Pascale Gourdeau, on the computability of robust learning http://
arxiv.org/abs/2406.10161 -
Challenges in Characterizing Distribution Learning Research
By
–
After lunch and a great poster session, @ToscaLechner continues with challenges in the way of characterizing distribution learning http://
arxiv.org/abs/2304.08712 -
ML Publishing Standards: Open Access and Protection Against Predatory Journals
By
–
Fortunately, in ML, this video is largely irrelevant. All reputable venues (NeurICMLR, T/JMLR, etc) don't charge publication costs, are open access, and allow arXiv posting.
— Gautam Kamath (@thegautamkamath) 28 novembre 2024
Unfortunately, some bad actors also try to enter the space and break this nice equilibrium, eg Nature MI https://t.co/wvYSAYmHBjFortunately, in ML, this video is largely irrelevant. All reputable venues (NeurICMLR, T/JMLR, etc) don't charge publication costs, are open access, and allow arXiv posting. Unfortunately, some bad actors also try to enter the space and break this nice equilibrium, eg Nature MI
-
Highlighting Student Lightning Talks from Salon ML Members
By
–
Lots of great student lighting talks — I'll highlight the ones by @TheSalonML members Matt Regehr (on https://
arxiv.org/abs/2405.20769) and @argymouz (on https://
arxiv.org/abs/2405.20405). -
Measuring Similarity Methods for Generative Models
By
–
And Ruth Urner discusses methods for measuring similarity of generative models.
-
Subjective Retrospective of 20 Years of Domain Adaptation
By
–
Shai Ben-David (@shaibendavid5), always full of strong perspectives, gives a "subjective" retrospective on 20 years of domain adaptation.
-
Vector Institute ML Theory Workshop with Leading Researchers
By
–
At the second @VectorInst ML theory workshop today! Ft a bunch of great folks including @ashtiani_hassan @MihaiCNica @shaibendavid5 @ToscaLechner @argymouz and more. Thanks to organizers Shai and Ruth Urner for giving me another chance to spread the gospel of robust estimation.