Yuval Dagan
@YuvalDagan3
Followers
449
Following
92
Media
3
Statuses
41
RT @KonstDaskalakis: Exciting work w/ @YuvalDagan3 @MFishelson @GolowichNoah on efficient algos for no-swap regret learning and, relatedly,….
0
9
0
RT @giannis_daras: Stable Diffusion and other text-to-image models sometimes blatantly copy from their training images. We introduce Ambie….
0
52
0
At COLT 2023! Learning and Testing Latent-Tree Ising Models Efficiently. Given i.i.d samples from the leaves of some evolutionary tree, we learn it in TV. Proof relies on a tensorization argument for latent models. w. V Kandiros, C Daskalakis and D Choo.
arxiv.org
We provide time- and sample-efficient algorithms for learning and testing latent-tree Ising models, i.e. Ising models that may only be observed at their leaf nodes. On the learning side, we obtain...
2
4
30
RT @IdanAttias: We studied the setting of semi-supervised adversarially robust PAC learning. Perhaps surprisingly, we show that the labeled….
0
7
0
RT @giannis_daras: Announcing Soft Diffusion: A framework to correctly schedule, learn and sample from general diffusion processes. State-….
0
69
0
RT @giannis_daras: New ICML paper: Score-Guided Intermediate Layer Optimization (SGILO). We train diffusion models on the latent space of….
0
13
0
RT @giannis_daras: DALLE-2 has a secret language. "Apoploe vesrreaitais" means birds. "Contarra ccetnxniams luryca tanniounons" means bug….
0
2K
0
RT @MHop_Theory: Wow! Brukhim, Carmon, Dinur, Moran, and Yehudayoff just resolved a long-standing open question on multi-class learning.….
0
9
0
RT @IdanAttias: Happy to share with you a new paper with Steve Hanneke and @YishayMansour:.A Characterization of Semi-Supervised Adversaria….
0
3
0
We've analyzed differential-privacy mechanisms that add bounded noise, and it usually outperforms the Gaussian mechanism! (if you consider a uniform bound on the noises of > 1000 queries) .new revision: (Joint with Gil Kur)
2
0
11
RT @AcmSIGecom: The @AcmSIGecom Dissertation Award for 2020 goes to .Manolis Zampetakis for his thesis "Statistics in High Dimensions witho….
0
10
0
RT @KSHartnett: A statistics postdoc has solved an important "slicing" problem in convex geometry. @EricaKlarreich reports in her terrific….
quantamagazine.org
To the surprise of experts in the field, a postdoctoral statistician has solved one of the most important problems in high-dimensional convex geometry.
0
19
0
The following paper (accepted to STOC 21) studies sampling algorithms on a stream, against an adversary that has access to the internal state of the algorithm. Further, it resolves an open question in online classification.
3
19
159
Have you wondered how to win the game "Twenty questions" with lies?.Now on ITCS, joint with Yuval Filmus @YFilmus, Daniel Kane and Shay Moran.
0
0
9
RT @KonstDaskalakis: Samples from high-dimensional distributions can be scarce or expensive to acquire. Can we meaningfully learn them from….
arxiv.org
There have been two separate lines of work on estimating Ising models: (1) estimating them from multiple independent samples under minimal assumptions about the model's interaction matrix; and (2)...
0
5
0
RT @KonstDaskalakis: Min-max optimization (used among other applications in GANs, and adversarial training more broadly) is empirically cha….
0
68
0
Thanks Gautam!!.
Amazing! Preprint by Yuval Dagan (@YuvalDagan3) & Gil Kur (@GilKur1) solves an open problem of Steinke (@shortstein) & Ullman (@thejonullman)! They shaved the last sqrt(log log log k) factor for answering k queries, winning themselves a sushi dinner! 🍣🍣🍣
1
1
27