Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Ashwin Pananjady"'
Publikováno v:
IEEE Transactions on Information Theory. 68:1851-1885
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a90de091db72ca9f2d6734fc650e9162
https://doi.org/10.1109/tit.2021.3130717
https://doi.org/10.1109/tit.2021.3130717
Publikováno v:
The Annals of Statistics. 51
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f30ea525cbfddadf849111e966f0afb
https://doi.org/10.1214/22-aos2246
https://doi.org/10.1214/22-aos2246
Publikováno v:
Mathematics of Operations Research.
Linear fixed-point equations in Hilbert spaces arise in a variety of settings, including reinforcement learning, and computational methods for solving differential and integral equations. We study methods that use a collection of random observations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ce54c560658019640608932d70e50be
https://doi.org/10.1287/moor.2022.1341
https://doi.org/10.1287/moor.2022.1341
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a21bfc9fb3fd181ca76438e2a3c715ec
https://doi.org/10.1109/cdc51059.2022.9993276
https://doi.org/10.1109/cdc51059.2022.9993276
Autor:
Dean P. Foster, Ashwin Pananjady
Publikováno v:
IEEE Transactions on Information Theory. 67:4092-4124
A single-index model is given by $y = g^{*}(\langle x, \theta ^{*} \rangle) + \epsilon $ : The scalar response $y$ depends on the covariate vector $x$ both through an unknown (vector) parameter ${\theta ^{*}}$ as well as an unknown, non-parametric, u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc34a63671eeefb19cfe684aab7e8faf
https://doi.org/10.1109/tit.2021.3075142
https://doi.org/10.1109/tit.2021.3075142
Autor:
Martin J. Wainwright, Ashwin Pananjady
Publikováno v:
IEEE Transactions on Information Theory. 67:566-585
Markov reward processes (MRPs) are used to model stochastic phenomena arising in operations research, control engineering, robotics, and artificial intelligence, as well as communication and transportation networks. In many of these cases, such as in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60d9d775c65ca64be264a4607b968fb3
https://doi.org/10.1109/tit.2020.3027316
https://doi.org/10.1109/tit.2020.3027316
We study the problem of policy evaluation with linear function approximation and present efficient and practical algorithms that come with strong optimality guarantees. We begin by proving lower bounds that establish baselines on both the determinist
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e2f8dc63697e8a8a2fc427c4c69c243
http://arxiv.org/abs/2112.13109
http://arxiv.org/abs/2112.13109
Publikováno v:
ISIT
We study the max-affine regression model, where the unknown regression function is modeled as a maximum of a fixed number of affine functions. In recent work [1], we showed that end-to-end parameter estimates were obtainable using this model with an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31699a80cbb13c6f74c032dad6003a39
https://doi.org/10.1109/isit44484.2020.9174116
https://doi.org/10.1109/isit44484.2020.9174116
Publikováno v:
Ann. Statist. 48, no. 2 (2020), 1072-1097
Pairwise comparison data arises in many domains, including tournament rankings, web search and preference elicitation. Given noisy comparisons of a fixed subset of pairs of items, we study the problem of estimating the underlying comparison probabili
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e589b3963556d90c8b748fa6a2860f6
https://doi.org/10.1214/19-aos1838
https://doi.org/10.1214/19-aos1838
We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local mini
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9ec55dea340dfbe29aa595409204987d