daniel hsu

@[email protected]

[daniel hsu @djhsu]

@sushnt congratulations, Sushant!!

[daniel hsu @djhsu]

@ccanonne_ I hear AdaBoost is the best off-the-shelf classifier in the world

[Francesco Orabona @bremen79]

ALT 2023 accepted papers
https://t.co/hbLGLwEY0v

[Jeremy Cohen @deepcohen]

This is an interesting new paper on the topic of feature learning. They show that several aspects of feature learning in neural nets can be reproduced in a simpler kernel-based model dubbed a “Recursive Feature Machine” (RFM) https://t.co/J6xjrRHL9i

[Rasmus Pagh @RasmusPagh1]

TheoretiCS has launched its first issue! https://t.co/AEBgg4ezcN
TheoretiCS is a new, peer-reviewed Diamond Open Access electronic journal covering all areas of Theoretical Computer Science. Looking forward to seeing how the journal develops.

[daniel hsu @djhsu]

@karlrohe apparently there is some progress https://t.co/89q6WpI3zV

[daniel hsu @djhsu]

@karlrohe You might be interested in the conjecture of Ray/Sturmfels https://t.co/B3gbNH7Lsy pp.7-8

[daniel hsu @djhsu]

https://t.co/UYhBRW8XcY

[Adel Javanmard @AdelJavanmard]

One of my pet peeves is this thing in US culture which urges people to come up with a "cool" story of their life, starting from a poor miserable state, shining into a successful career. It pushes people to come up with bipolar exaggerated narrative of their life ....

[Colin Wright (@[email protected]) @ColinTheMathmo]

The Twitter war against Mastodon in general continues. Various links to Mastodon sites are now being marked as potentially unsafe.

I was going to post a link to the discussion, but Twitter won't let me. So I've charted it so you can see it:

https://t.co/MoNtPQRutU

[Gautam Kamath @thegautamkamath]

🧵New paper w Nicholas Carlini & @florian_tramer: "Considerations for Differentially Private Learning with Large-Scale Public Pretraining."

We critique the increasingly popular use of large-scale public pretraining in private ML.

Comments welcome.

https://t.co/Gh4CmBzMNm 1/n

[ML-NYC Speaker Series @MLNYCSeries]

We're excited to welcome Lawrence Saul as our next speaker on Thursday Dec 15 at 4pm!

Title: A Geometrical Connection Between Sparse and Low-rank Matrices and Its Uses for Machine Learning

Register here: https://t.co/Lp8BQHbk4B

[daniel hsu @djhsu]

@miniapeur @CindyRush https://t.co/4QfcWXDtgE

[daniel hsu @djhsu]

@gabrielpeyre @adad8m (replacing 4 with 3 everywhere also works)

[daniel hsu @djhsu]

@gabrielpeyre @adad8m Try the 4-dim discrete hypercube {-1,1}^4 with p=4. I think you are basically looking for lp metrics that are not negative type.

[daniel hsu @djhsu]

@thegautamkamath @_kunal_talwar_ Yeah, email by shell script is only acceptable for recruiting PC members

[daniel hsu @djhsu]

@Adam235711 @boydgraber @thegautamkamath @CSrankings But they don't list affiliates on the that website anyway... best to stick to Sariel's cs_ranking https://t.co/sdc94PnRt8

[daniel hsu @djhsu]

@Adam235711 @boydgraber @thegautamkamath @CSrankings Yes they can

[daniel hsu @djhsu]

@Adam235711 @boydgraber @thegautamkamath @CSrankings https://t.co/2zGyJPCrfE

[daniel hsu @djhsu]

@beenwrekt @itsrainingdata @ducha_aiki uhhhh yours?????????