Zobrazeno 1 - 10
of 999
pro vyhledávání: '"Vidyasagar, M"'
Autor:
Karandikar, Rajeeva L., Vidyasagar, M.
In this paper, we study the convergence properties of the Stochastic Gradient Descent (SGD) method for finding a stationary point of a given objective function $J(\cdot)$. The objective function is not required to be convex. Rather, our results apply
Externí odkaz:
http://arxiv.org/abs/2312.02828
In this paper, we present a unified and general framework for analyzing the batch updating approach to nonlinear, high-dimensional optimization. The framework encompasses all the currently used batch updating approaches, and is applicable to nonconve
Externí odkaz:
http://arxiv.org/abs/2209.05372
Autor:
Vidyasagar, M.
In this paper, we study the almost sure boundedness and the convergence of the stochastic approximation (SA) algorithm. At present, most available convergence proofs are based on the ODE method, and the almost sure boundedness of the iterations is an
Externí odkaz:
http://arxiv.org/abs/2205.01303
Autor:
Karandikar, Rajeeva L., Vidyasagar, M.
We begin by briefly surveying some results on the convergence of the Stochastic Gradient Descent (SGD) Method, proved in a companion paper by the present authors. These results are based on viewing SGD as a version of Stochastic Approximation (SA). E
Externí odkaz:
http://arxiv.org/abs/2109.03445
Autor:
Kaushal, Shaurya, Rajput, Abhineet Singh, Bhattacharya, Soumyadeep, Vidyasagar, M., Kumar, Aloke, Prakash, Meher K., Ansumali, Santosh
A quantitative COVID-19 model that incorporates hidden asymptomatic patients is developed, and an analytic solution in parametric form is given. The model incorporates the impact of lockdown and resulting spatial migration of population due to announ
Externí odkaz:
http://arxiv.org/abs/2006.00045
Autor:
Vidyasagar, M.1 (AUTHOR) m.vidyasagar@iith.ac.in
Publikováno v:
Mathematics of Control, Signals & Systems. Jun2023, Vol. 35 Issue 2, p351-374. 24p.
Autor:
Ahsen, M. Eren, Vidyasagar, M.
In compressed sensing, in order to recover a sparse or nearly sparse vector from possibly noisy measurements, the most popular approach is $\ell_1$-norm minimization. Upper bounds for the $\ell_2$- norm of the error between the true and estimated vec
Externí odkaz:
http://arxiv.org/abs/1512.08673
Autor:
Chakrabarty Jyothi, Vidyasagar M S
Publikováno v:
Forum of Clinical Oncology, Vol 11, Iss 3, Pp 17-22 (2021)
Though Yoga has originated in India, its scientific use to alleviate the sufferings of cancer patients in India is thin. There are very few published studies on yoga intervention for cancer patients from India. The objective of this review was to ana
Externí odkaz:
https://doaj.org/article/7a335eb6fc4b4449a9e5749f98843990
Autor:
Rahul Ganpatrao Sonkamble, Shraddha P. Phansalkar, Vidyasagar M. Potdar, Anupkumar M. Bongale
Publikováno v:
IEEE Access, Vol 9, Pp 158367-158401 (2021)
Interoperability in Electronic Health Records (EHR) is significant for the seamless sharing of information amongst different healthcare stakeholders. Interoperability in EHR aims to devise agreements in its interpretation, access, and storage with se
Externí odkaz:
https://doaj.org/article/078bb8db915c4460975e2ba91895fc96