Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Siddhartha Satpathi"'
Publikováno v:
IEEE Transactions on Automatic Control, 68 (5)
In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms, projection-free an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a8da1fa6a1302c63490b66bcd7d28801
http://arxiv.org/abs/2103.01391
http://arxiv.org/abs/2103.01391
Publikováno v:
CDC
In this paper, we consider gradient descent on a regularized loss function for training an overparametrized neural network. We model the algorithm as an ODE and show how overparameterization and regularization work together to provide the right trade
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f21d7701890ef829c29411cd905d898
https://doi.org/10.1109/cdc42340.2020.9304386
https://doi.org/10.1109/cdc42340.2020.9304386
Publikováno v:
Applied and Computational Harmonic Analysis. 43:568-576
In compressive sensing, one important parameter that characterizes the various greedy recovery algorithms is the iteration bound which provides the maximum number of iterations by which the algorithm is guaranteed to converge. In this letter, we pres
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::656f0ec6cd6451deea67357b0846c916
https://doi.org/10.1016/j.acha.2016.10.001
https://doi.org/10.1016/j.acha.2016.10.001
Publikováno v:
IEEE Transactions on Information Theory. 62:6508-6534
Group-based sparsity models are proven instrumental in linear regression problems for recovering signals from much fewer measurements than standard compressive sensing. The main promise of these models is the recovery of "interpretable" signals throu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d899b6a243a1fa074614d1038842b7d
https://doi.org/10.1109/tit.2016.2602222
https://doi.org/10.1109/tit.2016.2602222
Publikováno v:
SPCOM
Recently, multiple orthogonal least squares (mOLS) was proposed as an extension of the well known orthogonal least squares (OLS) algorithm, which generalizes the support identification strategy of OLS by selecting multiple columns per iteration, ther
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d2618fb9ad9c587294a0aa80c7eb388
https://doi.org/10.1109/spcom.2018.8724462
https://doi.org/10.1109/spcom.2018.8724462
We consider the problem of separating error messages generated in large distributed data center networks into error events. In such networks, each error event leads to a stream of messages generated by hardware and software components affected by the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5eda7009726e3b945cdaea2617e2c9b
http://arxiv.org/abs/1804.03346
http://arxiv.org/abs/1804.03346
Publikováno v:
IEEE Signal Processing Letters. 20:1074-1077
The generalized Orthogonal Matching Pursuit (gOMP) is a recently proposed compressive sensing greedy recovery algorithm which generalizes the OMP algorithm by selecting N( ≥ 1) atoms in each iteration. In this letter, we demonstrate that the gOMP c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::772470c18c09dfd61302f5eda3e10ccd
https://doi.org/10.1109/lsp.2013.2279977
https://doi.org/10.1109/lsp.2013.2279977
Orthogonal least square (OLS) is an important sparse signal recovery algorithm for compressive sensing, which enjoys superior probability of success over other well-known recovery algorithms under conditions of correlated measurement matrices. Multip
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d34f92f8d11057af24b061e2d2e8ccc3
http://arxiv.org/abs/1511.08575
http://arxiv.org/abs/1511.08575
Publikováno v:
ISIT
We consider the problem of finding a K-sparse approximation of a signal, such that the support of the approximation is the union of sets from a given collection, a.k.a. group structure. This problem subsumes the one of finding K-sparse tree approxima
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6f1a4092d9e6d7d7fa8957387076c85
https://doi.org/10.1109/isit.2015.7282515
https://doi.org/10.1109/isit.2015.7282515
Publikováno v:
ICC
A joint transmitter-receiver energy harvesting model is considered, where both the transmitter and receiver are powered by (renewable) energy harvesting source. Given a fixed number of bits, the problem is to find the optimal transmission power profi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ad2cb7bde965b9f26c0e9effb6c60214