daniel hsu

45 posts

daniel hsu banner
daniel hsu

daniel hsu

@djhsu

@[email protected]

Katılım Ocak 2009
422 Takip Edilen1.4K Takipçiler
Sushant Sachdeva
Sushant Sachdeva@sushnt·
Thrilled and honored to be a part of this year's cohort of Sloan Fellows. Deep gratitude to my collaborators and students without whom the work I'm part of would be impossible, and to my mentors and my family for their unwavering support. 🙏🏽 #SloanFellow
Sloan Foundation@SloanFoundation

We are delighted to announce the winners of this year’s Sloan Research Fellowship! These outstanding researchers are shining examples of innovation and impact—and we are thrilled to support them. Meet the winners here: sloan.org/fellowships/20… 🎉 #SloanFellow #STEM #ScienceTwitter

English
28
2
141
31.9K
daniel hsu
daniel hsu@djhsu·
@ccanonne_ I hear AdaBoost is the best off-the-shelf classifier in the world
English
0
0
15
4.6K
daniel hsu retweetledi
Jeremy Cohen
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) arxiv.org/abs/2212.13881
English
6
36
221
48.7K
daniel hsu retweetledi
Rasmus Pagh
Rasmus Pagh@RasmusPagh1·
TheoretiCS has launched its first issue! theoretics.episciences.org/volume/view/id… 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.
English
1
15
32
5.7K
daniel hsu retweetledi
Adel Javanmard
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 ....
English
1
1
7
2.6K
daniel hsu retweetledi
Colin Wright (@ColinTheMathmo@mathstodon.xyz)
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: solipsys.co.uk/Chartodon/1095…
English
1
3
4
1.2K
daniel hsu retweetledi
Gautam Kamath
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. arxiv.org/abs/2212.06470 1/n
Gautam Kamath tweet media
English
4
19
143
0
daniel hsu retweetledi
ML-NYC Speaker Series
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: eventbrite.com/e/ml-nyc-speak…
English
0
6
11
0
Mathieu
Mathieu@miniapeur·
@CindyRush Any breakthroughs that I am not aware of?
English
2
0
0
0
Cindy Rush
Cindy Rush@CindyRush·
💥💥💥 nuclear fusion 💥💥💥
English
2
0
11
0
daniel hsu
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.
English
1
0
3
0
Gautam Kamath
Gautam Kamath@thegautamkamath·
@_kunal_talwar_ If someone's using a shell script to contact potential supervisors, I think they're doing something wrong...
English
2
1
7
0
Gautam Kamath
Gautam Kamath@thegautamkamath·
I think @CSrankings is a helpful resource. I don't care about the "rankings". But I like that it's a single place to find a *list* of people active in a research area. If you're a faculty in CS, you should make sure you're listed there. csrankings.org
English
14
8
171
0
Ben Recht
Ben Recht@beenwrekt·
Fascinating conversation here. And it leaves us with a rephrasing of the question @ducha_aiki was asking: "Why do ML models trained to predict discrete labels work so much better than those trained to predict real-valued labels?" Thoughts?
Ben Recht@beenwrekt

I know everyone has left for Mastodon, but this tweet has inspired an interesting conversation on ML Twitter. It left me asking: What does “regression” mean to you in the context of machine learning? twitter.com/ducha_aiki/sta…

English
4
1
22
0