Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Kunal Talwar"'
Publikováno v:
Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA) ISBN: 9781611977554
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c68789030b53a0f4e8e13c2ff3a43d69
https://doi.org/10.1137/1.9781611977554.ch181
https://doi.org/10.1137/1.9781611977554.ch181
Publikováno v:
University of Twente Research Information (Pure Portal)
Uniform stability is a notion of algorithmic stability that bounds the worst case change in the model output by the algorithm when a single data point in the dataset is replaced. An influential work of Hardt et al. (2016) provides strong upper bounds
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af45baedbd7eaf0a8e5e21b553359058
Publikováno v:
STOC
Modern machine learning models are complex and frequently encode surprising amounts of information about individual inputs. In extreme cases, complex models appear to memorize entire input examples, including seemingly irrelevant information (social
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e37f2a89a8dddcb3c8b40755096da4b
Publikováno v:
STOC
We study differentially private (DP) algorithms for stochastic convex optimization: the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. (2019) has establis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::712711c61035cba403d697e18cd06170
Publikováno v:
SIAM Journal on Computing. 45:575-616
In this work, we study trade-offs between accuracy and privacy in the context of linear queries over histograms. This is a rich class of queries that includes contingency tables and range queries and has been a focus of a long line of work. For a giv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::88c7fe607a687cae2b21fd41e4ba2d24
https://doi.org/10.1137/130938943
https://doi.org/10.1137/130938943
Autor:
Kunal Talwar, Jingcheng Liu
Publikováno v:
STOC
Differentially Private algorithms often need to select the best amongst many candidate options. Classical works on this selection problem require that the candidates' goodness, measured as a real-valued score function, does not change by much when on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::08a660d7485ca33af11e895c84eb30a2
http://arxiv.org/abs/1811.07971
http://arxiv.org/abs/1811.07971
Publikováno v:
FOCS
In the vector balancing problem, we are given symmetric convex bodies C and K in R^n, and our goal is to determine the minimum number β ≥ 0, known as the vector balancing constant from C to K, such that for any sequence of vectors in C there alway
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::adb09b0db23e590f57b671fe753a74e3
https://ir.cwi.nl/pub/28419
https://ir.cwi.nl/pub/28419
Publikováno v:
FOCS
Many commonly used learning algorithms work by iteratively updating an intermediate solution using one or a few data points in each iteration. Analysis of differential privacy for such algorithms often involves ensuring privacy of each step and then
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::598cd0af69290662a63e2f43f1fe5edf
https://doi.org/10.1109/focs.2018.00056
https://doi.org/10.1109/focs.2018.00056
Autor:
Jason M. Altschuler, Kunal Talwar
This paper studies the value of switching actions in the Prediction From Experts (PFE) problem and Adversarial Multi-Armed Bandits (MAB) problem. First, we revisit the well-studied and practically motivated setting of PFE with switching costs. Many a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a32a77d19ec3e985f491de30482cba58