Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Theory of computation → Machine learning theory"'
Autor:
Holmgren, Justin, Jawale, Ruta
The goal of a covert learning algorithm is to learn a function f by querying it, while ensuring that an adversary, who sees all queries and their responses, is unable to (efficiently) learn any more about f than they could learn from random input-out
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1aff0642eaa1118b3b49a27b3ecdbdb8
We consider the problem of helping agents improve by setting goals. Given a set of target skill levels, we assume each agent will try to improve from their initial skill level to the closest target level within reach (or do nothing if no target level
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::acff7663ac7c7accd708015d65d82989
This report documents the program and the outcomes of Dagstuhl Perspectives Workshop 22262 "Human-Centered Artificial Intelligence". The goal of this Dagstuhl Perspectives Workshops is to provide the scientific and technological foundations for desig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::305da92333fe26324b4bbd0900cb7c5a
Publikováno v:
ACM Transactions on Database Systems, 47(4):14. Association for Computing Machinery (ACM)
24th International Conference on Database Theory: ICDT 2021, March 23-26, 2021, Nicosia, Cyprus
24th International Conference on Database Theory
24th International Conference on Database Theory: ICDT 2021, March 23-26, 2021, Nicosia, Cyprus
24th International Conference on Database Theory
We answer the question of which conjunctive queries are uniquely characterized by polynomially many positive and negative examples, and how to construct such examples efficiently. As a consequence, we obtain a new efficient exact learning algorithm f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9c9c88d6394ba78cfa6346f9ea0b05c
https://doi.org/10.1145/3559756
https://doi.org/10.1145/3559756
Autor:
Du, Elbert, Dwork, Cynthia
Differential privacy is known to protect against threats to validity incurred due to adaptive, or exploratory, data analysis -- even when the analyst adversarially searches for a statistical estimate that diverges from the true value of the quantity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e696642a097a4e786bc39a0dc076778
http://arxiv.org/abs/2207.10668
http://arxiv.org/abs/2207.10668
Suppose we are given two datasets: a labeled dataset and unlabeled dataset which also has additional auxiliary features not present in the first dataset. What is the most principled way to use these datasets together to construct a predictor? The ans
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47f9cc481e5a698fcb909fce44a04ba7
Autor:
Chowdhury, Sadia, Urner, Ruth
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability and trustworthiness: in many instances an imperceptible perturbation can falsely flip a neural network’s prediction. Applied resear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::96038abf186e2a76a8d85f75bb4e0cab
Autor:
Celis, L. Elisa
Front Matter, Table of Contents, Preface, Conference Organization
LIPIcs, Vol. 218, 3rd Symposium on Foundations of Responsible Computing (FORC 2022), pages 0:i-0:x
LIPIcs, Vol. 218, 3rd Symposium on Foundations of Responsible Computing (FORC 2022), pages 0:i-0:x
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3d252c54787a86f87dfc3942b6690dc
Publikováno v:
[Research Report] CISPA Helmholtz Center for Information Security, Saarbrücken, Germany; Aix-Marseile Université, France. 2022
MFCS 2022--47th International Symposium on Mathematical Foundations of Computer Science
MFCS 2022--47th International Symposium on Mathematical Foundations of Computer Science, 2022, Vienna, Austria. pp.31:1--31:14, ⟨10.4230/LIPIcs.MFCS.2022.31⟩
MFCS 2022--47th International Symposium on Mathematical Foundations of Computer Science
MFCS 2022--47th International Symposium on Mathematical Foundations of Computer Science, 2022, Vienna, Austria. pp.31:1--31:14, ⟨10.4230/LIPIcs.MFCS.2022.31⟩
One of the open problems in machine learning is whether any set-family of VC-dimension $d$ admits a sample compression scheme of size~$O(d)$. In this paper, we study this problem for balls in graphs. For balls of arbitrary radius $r$, we design prope
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::039bd19761d383e2e26559cb2b4dc038
https://hal.archives-ouvertes.fr/hal-03705798
https://hal.archives-ouvertes.fr/hal-03705798
Autor:
Hu, Lunjia, Peale, Charlotte
In many learning theory problems, a central role is played by a hypothesis class: we might assume that the data is labeled according to a hypothesis in the class (usually referred to as the realizable setting), or we might evaluate the learned model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75a9f7afddd30a513277f0c38138ec0c