M. Vidyasagar
YOU?
Author Swipe
View article: Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters
Convergence of Momentum-Based Optimization Algorithms with Time-Varying Parameters Open
In this paper, we present a unified algorithm for stochastic optimization that makes use of a "momentum" term; in other words, the stochastic gradient depends not only on the current true gradient of the objective function, but also on the…
View article: A vector almost-supermartingale convergence theorem and its applications
A vector almost-supermartingale convergence theorem and its applications Open
International audience
View article: Constant step-size stochastic approximation with delayed updates
Constant step-size stochastic approximation with delayed updates Open
International audience
View article: Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications
Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications Open
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 $$J(\cdot )$$ J ( · ) . The objective function is not required to be convex. Ra…
View article: 2023 Ninth Indian Control Conference (ICC)
2023 Ninth Indian Control Conference (ICC) Open
Recent radical evolution in distributed sensing, computation, communication, and actuation has fostered the emergence of cyber-physical network systems.Regardless of the specific application, one central goal is to shape the network's coll…
View article: Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications
Convergence Rates for Stochastic Approximation: Biased Noise with Unbounded Variance, and Applications Open
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 re…
View article: A tutorial introduction to reinforcement learning
A tutorial introduction to reinforcement learning Open
In this paper, we present a brief survey of reinforcement learning, with particular emphasis on stochastic approximation (SA) as a unifying theme. The scope of the paper includes Markov reward processes, Markov decision processes, SA algor…
View article: A Tutorial Introduction to Reinforcement Learning
A Tutorial Introduction to Reinforcement Learning Open
In this paper, we present a brief survey of Reinforcement Learning (RL), with particular emphasis on Stochastic Approximation (SA) as a unifying theme. The scope of the paper includes Markov Reward Processes, Markov Decision Processes, Sto…
View article: Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updating
Convergence of the Stochastic Heavy Ball Method With Approximate Gradients and/or Block Updating Open
In this paper, we establish the convergence of the stochastic Heavy Ball (SHB) algorithm under more general conditions than in the current literature. Specifically, (i) The stochastic gradient is permitted to be biased, and also, to have c…
View article: A prospective evaluation of breast thermography enhanced by a novel machine learning technique for screening breast abnormalities in a general population of women presenting to a secondary care hospital
A prospective evaluation of breast thermography enhanced by a novel machine learning technique for screening breast abnormalities in a general population of women presenting to a secondary care hospital Open
Objective Artificial intelligence-enhanced breast thermography is being evaluated as an ancillary modality in the evaluation of breast disease. The objective of this study was to evaluate the clinical performance of Thermalytix, a CE-marke…
View article: Front Matter
Front Matter Open
8 and acquired the Proceedings for inclusion in IEEE Xplore.In addition, the Outreach Fund of the IEEE Control Systems Society has awarded $ 7080 ($ 6000 + 18% Goods and Services Tax) to ICC-8.The Outreach Fund is being used to promote stu…
View article: Estimating large causal polytrees from small samples
Estimating large causal polytrees from small samples Open
We consider the problem of estimating a large causal polytree from a relatively small i.i.d. sample. This is motivated by the problem of determining causal structure when the number of variables is very large compared to the sample size, s…
View article: Automated vascular analysis of breast thermograms with interpretable features
Automated vascular analysis of breast thermograms with interpretable features Open
Purpose: Vascular changes are observed from initial stages of breast cancer, and monitoring of vessel structures helps in early detection of malignancies. In recent years, thermal imaging is being evaluated as a low-cost imaging modality t…
View article: Modified Error Bounds for Matrix Completion and Application to RL
Modified Error Bounds for Matrix Completion and Application to RL Open
In matrix completion under noisy measurements, most available results assume that there is an a priori bound on the Frobenius norm of the noise, and derive bounds on the Frobenius norm of the residual error. In this letter, we obtain “comp…
View article: Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning
Convergence of Batch Asynchronous Stochastic Approximation With Applications to Reinforcement Learning Open
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 Approximat…
View article: SUTRA: A Novel Approach to Modelling Pandemics with Asymptomatic and Undetected Patients, and Applications to COVID-19
SUTRA: A Novel Approach to Modelling Pandemics with Asymptomatic and Undetected Patients, and Applications to COVID-19 Open
In this paper, we present a new mathematical model for pandemics that have asymptomatic patients many of whom remain undetected, called SUTRA. The acronym stands for Susceptible, Undetected, Tested (positive), and Removed Approach. There a…
View article: New and explicit constructions of unbalanced Ramanujan bipartite graphs
New and explicit constructions of unbalanced Ramanujan bipartite graphs Open
The objectives of this article are threefold. Firstly, we present for the first time explicit constructions of an infinite family of unbalanced Ramanujan bigraphs. Secondly, we revisit some of the known methods for constructing Ramanujan g…
View article: SUTRA: A Novel Approach to Modelling Pandemics with Applications to\n COVID-19
SUTRA: A Novel Approach to Modelling Pandemics with Applications to\n COVID-19 Open
The Covid-19 pandemic has two key properties: (i) asymptomatic cases (both\ndetected and undetected) that can result in new infections, and (ii)\ntime-varying characteristics due to new variants, Non-Pharmaceutical\nInterventions etc. We d…
View article: SUTRA: A Novel Approach to Modelling Pandemics with Applications to COVID-19
SUTRA: A Novel Approach to Modelling Pandemics with Applications to COVID-19 Open
The Covid-19 pandemic has two key properties: (i) asymptomatic cases (both detected and undetected) that can result in new infections, and (ii) time-varying characteristics due to new variants, Non-Pharmaceutical Interventions etc. We deve…
View article: Authors' response
Authors' response Open
Background & objectives: Healthcare workers (HCWs) are considered to be at a high risk of contracting COVID-19 infection. Besides, control of nosocomial infections transmitted from HCWs to the patients is also a cause of concern. This stud…
View article: Modelling the spread of SARS-CoV-2 pandemic - Impact of lockdowns & interventions
Modelling the spread of SARS-CoV-2 pandemic - Impact of lockdowns & interventions Open
Background & objectives: To handle the current COVID-19 pandemic in India, multiple strategies have been applied and implemented to slow down the virus transmission. These included clinical management of active cases, rapid development of …
View article: Estimating the herd immunity threshold by accounting for the hidden asymptomatics using a COVID-19 specific model
Estimating the herd immunity threshold by accounting for the hidden asymptomatics using a COVID-19 specific model Open
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 lock-down and resulting spatial migration of population d…
View article: Academic Relationships and Resources: Assessing the Impact on Quality of Education
Academic Relationships and Resources: Assessing the Impact on Quality of Education Open
The study is an empirical examination of how the academic relationship between Faculty and student, student’s access to resources affect the quality of education in higher education institutions across Andhra Pradesh, India. Data was colle…
View article: A Review on the Challenges in Indian Genomics Research for Variant Identification and Interpretation
A Review on the Challenges in Indian Genomics Research for Variant Identification and Interpretation Open
Today, genomic data holds great potential to improve healthcare strategies across various dimensions - be it disease prevention, enhanced diagnosis, or optimized treatment. The biggest hurdle faced by the medical and research community in …
View article: Estimating Hidden Asymptomatics, Herd Immunity Threshold and Lockdown Effects using a COVID-19 Specific Model
Estimating Hidden Asymptomatics, Herd Immunity Threshold and Lockdown Effects using a COVID-19 Specific Model Open
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 du…
View article: Modelling the COVID-19 Pandemic: Asymptomatic Patients, Lockdown and Herd Immunity
Modelling the COVID-19 Pandemic: Asymptomatic Patients, Lockdown and Herd Immunity Open
The SARS-Cov-2 is a type of coronavirus that has caused the COVID-19 pandemic. In traditional epidemiological models such as SEIR (Susceptible, Exposed, Infected, Removed), the exposed group E does not infect the susceptible group S. A dis…
View article: Deterministic Completion of Rectangular Matrices Using Asymmetric Ramanujan Graphs: Exact and Stable Recovery
Deterministic Completion of Rectangular Matrices Using Asymmetric Ramanujan Graphs: Exact and Stable Recovery Open
In this paper we study the matrix completion problem: Suppose $X \in {\mathbb R}^{n_r \times n_c}$ is unknown except for a known upper bound $r$ on its rank. By measuring a small number $m \ll n_r n_c$ of elements of $X$, is it possible to…
View article: Compressed Sensing Using Binary Matrices of Nearly Optimal Dimensions
Compressed Sensing Using Binary Matrices of Nearly Optimal Dimensions Open
In this paper, we study the problem of compressed sensing using binary measurement matrices and $\ell_1$-norm minimization (basis pursuit) as the recovery algorithm. We derive new upper and lower bounds on the number of measurements to ach…