Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Jacob Steinhardt"'
Publikováno v:
Journal of the ACM. 70:1-46
Large-scale, two-sided matching platforms must find market outcomes that align with user preferences while simultaneously learning these preferences from data. Classical notions of stability (Gale and Shapley, 1962; Shapley and Shubik, 1971) are, unf
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18e1c99cfb1753358095dc4abed042cc
https://doi.org/10.1145/3583681
https://doi.org/10.1145/3583681
Publikováno v:
Information and Inference: A Journal of the IMA. 11:581-636
We explore why many recently proposed robust estimation problems are efficiently solvable, even though the underlying optimization problems are non-convex. We study the loss landscape of these robust estimation problems, and identify the existence of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40ac56b21a37aca318d368508ebe9140
https://doi.org/10.1093/imaiai/iaab018
https://doi.org/10.1093/imaiai/iaab018
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a78106a5aed3bf317041b78f2319d9d
https://doi.org/10.1109/cvprw56347.2022.00535
https://doi.org/10.1109/cvprw56347.2022.00535
Autor:
Jacob Steinhardt, Zachary C. Lipton
Publikováno v:
Communications of the ACM. 62:45-53
Some ML papers suffer from flaws that could mislead the public and stymie future research.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68da0ffa24aa4e76df41d7c599147ff0
https://doi.org/10.1145/3316774
https://doi.org/10.1145/3316774
Autor:
Jacob Steinhardt, Zachary C. Lipton
Publikováno v:
Queue. 17:45-77
Flawed scholarship threatens to mislead the public and stymie future research by compromising ML’s intellectual foundations. Indeed, many of these problems have recurred cyclically throughout the history of AI and, more broadly, in scientific resea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f52582991d9b71275c733f7d62b5386
https://doi.org/10.1145/3317287.3328534
https://doi.org/10.1145/3317287.3328534
Publikováno v:
International Journal of Epidemiology
Background With reduced community mobility, household infections may become increasingly important in SARS-CoV-2 transmission dynamics. Methods We investigate the intra-household transmission of COVID-19 through the secondary-attack rate (SAR) and ho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::604009669b002255b0908368db5a5cfc
http://europepmc.org/articles/PMC8344712
http://europepmc.org/articles/PMC8344712
Autor:
Collin Burns, Jacob Steinhardt
Publikováno v:
CVPR
Feature alignment is an approach to improving robustness to distribution shift that matches the distribution of feature activations between the training distribution and test distribution. A particularly simple but effective approach to feature align
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f35303e6285ac20b258157fbd19bb2f5
http://arxiv.org/abs/2103.05898
http://arxiv.org/abs/2103.05898
Publikováno v:
Health affairs (Project Hope). 40(1)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::be2f353ea1dcfbb82cd40d3626a7f296
https://pubmed.ncbi.nlm.nih.gov/33400584
https://pubmed.ncbi.nlm.nih.gov/33400584
Publikováno v:
ACL/IJCNLP (Findings)
Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution robustness, while other work suggests they have lower accuracy on rare
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b1585ee6e84b2d606eba2700c6eb3276
Introduction and GoalsSARS-CoV-2 is transmitted both in the community and within households. Social distancing and lockdowns reduce community transmission but do not directly address household transmission. We provide quantitative measures of househo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::768f534502c55634fc9cad7448088b09
https://doi.org/10.1101/2020.05.23.20111559
https://doi.org/10.1101/2020.05.23.20111559