Zobrazeno 1 - 10
of 56
pro vyhledávání: '"YIN TAT LEE"'
Autor:
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
Publikováno v:
The Journal of Privacy and Confidentiality, Vol 14, Iss 2 (2024)
We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a meta-frame
Externí odkaz:
https://doaj.org/article/8346b4e076df4c3695c222783f15b79f
Publikováno v:
The Journal of Privacy and Confidentiality, Vol 14, Iss 1 (2024)
We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of \emph{privacy loss random variables} to quantify the privacy loss of DP algorithms.
Externí odkaz:
https://doaj.org/article/44a696bafb504c5c98397942016f3029
Publikováno v:
The Journal of Privacy and Confidentiality, Vol 14, Iss 1 (2024)
In this paper, we study private optimization problems for non-smooth convex functions $F(x)=\mathbb{E}_i f_i(x)$ on $\mathbb{R}^d$. We show that modifying the exponential mechanism by adding an $\ell_2^2$ regularizer to $F(x)$ and sampling from $\pi(
Externí odkaz:
https://doaj.org/article/d60e3180ef9a408d9b641f6ae913a0f3
Autor:
COHEN, MICHAEL B.1 micohen@mit.edu, YIN TAT LEE2 yintat@uw.edu, ZHAO SONG3 magic.linuxkde@gmail.com
Publikováno v:
Journal of the ACM. Jan2021, Vol. 68 Issue 1, p1-39. 39p.
Publikováno v:
Journal of the ACM; Jul2021, Vol. 68 Issue 4, p1-37, 37p
We present a nearly-linear time algorithm for finding a minimum-cost flow in planar graphs with polynomially bounded integer costs and capacities. The previous fastest algorithm for this problem is based on interior point methods (IPMs) and works for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5f8b169d645101da2ca9fda1628c99ea
https://eprints.gla.ac.uk/276835/3/276835.pdf
https://eprints.gla.ac.uk/276835/3/276835.pdf
Autor:
German Preciat, Agnieszka B. Wegrzyn, Edinson Lucumi Moreno, Cornelius C.W. Willacey, Jennifer Modamio, Fatima L. Monteiro, Diana El Assal, Alissa Schurink, Miguel A.P. Oliveira, Zhi Zhang, Ben Cousins, Hulda S. Haraldsdóttir, Siham Hachi, Susanne Zach, German Leparc, Yin Tat Lee, Bastian Hengerer, Santosh Vempala, Michael A. Saunders, Amy Harms, Enrico Glaab, Jens C. Schwamborn, Ines Thiele, Thomas Hankemeier, Ronan M.T. Fleming
Patient-derived cellular models are a powerful approach to study human disease, especially neurode-generative diseases, such as Parkinson’s disease, where affected primary neurons, e.g., substantia nigra dopaminergic neurons, are almost inaccessibl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bcc67eaf5b3fd1d397e56bcd6b6b301
https://doi.org/10.1101/2021.06.30.450562
https://doi.org/10.1101/2021.06.30.450562
Publikováno v:
STOC
We show that the volume of a convex body in Rn in the general membership oracle model can be computed to within relative error e using O(n3ψ2/e2) oracle queries, where ψ is the KLS constant. With the current bound of ψ=O(no(1)), this gives an O(n3
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::98fa3c80b94cf9a3aece0a57f924bfc2
https://doi.org/10.1145/3406325.3451018
https://doi.org/10.1145/3406325.3451018
Autor:
Santosh Vempala, Yin Tat Lee
Publikováno v:
STOC
We introduce the geodesic walk for sampling Riemannian manifolds and apply it to the problem of generating uniform random points from the interior of polytopes in ℝn specified by m inequalities. The walk is a discrete-time simulation of a stochasti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::366cd6a6ba403c2a26b0b90b3d4de6a6
https://doi.org/10.1137/17m1145999
https://doi.org/10.1137/17m1145999