Vivek S. Borkar

245 papers A* 4A 1B 6C 1Misc 7Journal 179Unranked 47

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A dynamic view of some anomalous phenomena in SGD for over-parametrized neural networks. Syst. Control. Lett. Vivek S. Borkar
2026	J	`jnl`	An Actor-Critic Algorithm With Function Approximation for Risk Sensitive Cost Markov Decision Processes. IEEE Trans. Autom. Control. Soumyajit Guin, Vivek S. Borkar, Shalabh Bhatnagar
2026	J	`jnl`	Lagrangian index policy for restless bandits with average reward. Queueing Syst. Theory Appl. Konstantin Avrachenkov, Vivek S. Borkar, Pratik Shah
2026	J	`jnl`	Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains. CoRR Rahul Singh, Siddharth Chandak, Eric Moulines, Vivek S. Borkar, Nicholas Bambos
2025	J	`jnl`	An Actor-Critic Algorithm with Function Approximation for Risk Sensitive Cost Markov Decision Processes. CoRR Soumyajit Guin, Vivek S. Borkar, Shalabh Bhatnagar
2025	J	`jnl`	Small noise limits of Markov chains and the PageRank. CoRR Vivek S. Borkar, S. Sowmya, Raghavendra Tripathi
2025	J	`jnl`	Some big issues with small noise limits in Markov decision processes. Syst. Control. Lett. Vivek S. Borkar
2025	J	`jnl`	Stochastic approximation in non-Markovian environments. Syst. Control. Lett. Vivek S. Borkar
2025	J	`jnl`	Whittle Index Based User Association in Dense Millimeter Wave Networks. IEEE Trans. Veh. Technol. Mandar R. Nalavade, Gaurav S. Kasbekar, Vivek S. Borkar
2024	J	`jnl`	Controlled Martingale Problems and Their Markov Mimics. SIAM J. Control. Optim. Siva Athreya, Vivek S. Borkar, Nitya Gadhiwala
2024	J	`jnl`	Lagrangian Index Policy for Restless Bandits with Average Reward. CoRR Konstantin Avrachenkov, Vivek S. Borkar, Pratik Shah
2024	J	`jnl`	Reinforcement learning in non-Markovian environments. Syst. Control. Lett. Siddharth Chandak, Pratik Shah, Vivek S. Borkar, Parth Dodhia
2024	J	`jnl`	Tabular and Deep Learning for the Whittle Index. CoRR Francisco Robledo Relaño, Vivek S. Borkar, Urtzi Ayesta, Konstantin Avrachenkov
2024	J	`jnl`	Tabular and Deep Learning for the Whittle Index. ACM Trans. Model. Perform. Evaluation Comput. Syst. Francisco Robledo Relaño, Vivek S. Borkar, Urtzi Ayesta, Konstantin Avrachenkov
2024	J	`jnl`	Whittle Index Based User Association in Dense Millimeter Wave Networks. CoRR Mandar R. Nalavade, Gaurav S. Kasbekar, Vivek S. Borkar
2023	J	`jnl`	A Concentration Bound for TD(0) with Function Approximation. CoRR Siddharth Chandak, Vivek S. Borkar
2023	J	`jnl`	A concentration bound for LSPE(λ). Syst. Control. Lett. Siddharth Chandak, Vivek S. Borkar, Harsh Dolhare
2023	J	`jnl`	Actor-Critic or Critic-Actor? A Tale of Two Time Scales. IEEE Control. Syst. Lett. Shalabh Bhatnagar, Vivek S. Borkar, Soumyajit Guin
2023	J	`jnl`	Approximation of Convex Envelope Using Reinforcement Learning. CoRR Vivek S. Borkar, Adit Akarsh
2023	J	`jnl`	Controlled Martingale Problems And Their Markov Mimics. CoRR Siva Athreya, Vivek S. Borkar, Nitya Gadhiwala
2023	J	`jnl`	Decentralised Q-Learning for Multi-Agent Markov Decision Processes with a Satisfiability Criterion. CoRR Keshav P. Keval, Vivek S. Borkar
2023	J	`jnl`	Ergodic risk-sensitive control - A survey. Annu. Rev. Control. Anup Biswas, Vivek S. Borkar
2023	—	`conf`	Full Gradient Deep Reinforcement Learning for Average-Reward Criterion. L4DC Tejas Pagare, Vivek S. Borkar, Konstantin Avrachenkov
2023	J	`jnl`	Full Gradient Deep Reinforcement Learning for Average-Reward Criterion. CoRR Tejas Pagare, Vivek S. Borkar, Konstantin Avrachenkov
2023	J	`jnl`	Node Cardinality Estimation in the Internet of Things Using Privileged Feature Distillation. CoRR Pranav S. Page, Anand S. Siyote, Vivek S. Borkar, Gaurav S. Kasbekar
2023	—	`conf`	Online Parameter Estimation in Partially Observed Markov Decision Processes. Allerton Sai Sumedh R. Hindupur, Vivek S. Borkar
2023	J	`jnl`	Special Issue : Multi-Agent Dynamic Decision Making and Learning. Dyn. Games Appl. Konstantin Avrachenkov, Vivek S. Borkar, U. Jayakrishnan Nair
2023	J	`jnl`	Stochastic control and stability with applications: Ari Arapostathis memorial issue. Syst. Control. Lett. Vivek S. Borkar, Prashant G. Mehta, Guodong Pang, Serdar Yüksel
2022	—	`conf`	A Concentration Bound for Distributed Stochastic Approximation. Allerton Harsh Dolhare, Vivek S. Borkar
2022	J	`jnl`	A Concentration Bound for Distributed Stochastic Approximation. CoRR Harsh Dolhare, Vivek S. Borkar
2022	J	`jnl`	Actor-Critic or Critic-Actor? A Tale of Two Time Scales. CoRR Shalabh Bhatnagar, Vivek S. Borkar, Soumyajit Guin
2022	J	`jnl`	Concentration bounds for SSP Q-learning for average cost MDPs. CoRR Shaan Ul Haque, Vivek S. Borkar
2022	J	`jnl`	Corrigendum to "A concentration bound for contractive stochastic approximation" [Syst. Control Lett. 153 (2021) 104947]. Syst. Control. Lett. Vivek S. Borkar
2022	J	`jnl`	Dynamic Social Learning Under Graph Constraints. IEEE Trans. Control. Netw. Syst. Konstantin E. Avrachenkov, Vivek S. Borkar, Sharayu Moharir, Suhail Mohmad Shah
2022	J	`jnl`	ERRATUM: LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The Nonergodic Case. SIAM J. Control. Optim. Vivek S. Borkar, Vladimir Gaitsgory, Ilya Shvartsman
2022	J	`jnl`	Learning to cooperate in agent-based control of queueing networks. Queueing Syst. Theory Appl. Vivek S. Borkar
2022	J	`jnl`	Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes. IEEE Trans. Autom. Control. Arghyadip Roy, Vivek S. Borkar, Abhay Karandikar, Prasanna Chaporkar
2022	J	`jnl`	Opinion Shaping in Social Networks Using Reinforcement Learning. IEEE Trans. Control. Netw. Syst. Vivek S. Borkar, Alexandre Reiffers-Masson
2022	J	`jnl`	QWI: Q-learning with Whittle Index. SIGMETRICS Perform. Evaluation Rev. Francisco Robledo, Vivek S. Borkar, Urtzi Ayesta, Konstantin Avrachenkov
2022	J	`jnl`	Reinforcement Learning in Non-Markovian Environments. CoRR Siddharth Chandak, Vivek S. Borkar, Parth Dodhia
2022	J	`jnl`	Revisiting SIR in the Age of COVID-19: Explicit Solutions and Control Problems. SIAM J. Control. Optim. Vivek S. Borkar, D. Manjunath
2022	—	`conf`	Scheduling in Wireless Networks using Whittle Index Theory. NCC Karthik G. V. B., Vivek S. Borkar, Gaurav S. Kasbekar
2022	J	`jnl`	Scheduling in Wireless Networks using Whittle Index Theory. CoRR Karthik G. V. B., Vivek S. Borkar, Gaurav S. Kasbekar
2022	J	`jnl`	User Association in Dense mmWave Networks as Restless Bandits. IEEE Trans. Veh. Technol. Santosh Kumar Singh, Vivek S. Borkar, Gaurav S. Kasbekar
2022	J	`jnl`	Whittle index based Q-learning for restless bandits with average reward. Autom. Konstantin E. Avrachenkov, Vivek S. Borkar
2022	J	`jnl`	Whittle indexability in egalitarian processor sharing systems. Ann. Oper. Res. Vivek S. Borkar, Sarath Pattathil
2021	J	`jnl`	A Concentration Bound for LSPE(λ). CoRR Vivek S. Borkar, Siddharth Chandak, Harsh Dolhare
2021	—	`conf`	A Unified Batch Selection Policy for Active Metric Learning. ECML/PKDD (2) Priyadarshini Kumari, Siddhartha Chaudhuri, Vivek S. Borkar, Subhasis Chaudhuri
2021	J	`jnl`	A concentration bound for contractive stochastic approximation. Syst. Control. Lett. Vivek S. Borkar
2021	—	`conf`	Accelerating MCMC by Rare Intermittent Resets. VALUETOOLS Vivek S. Borkar, Syomantak Chaudhuri
2021	J	`jnl`	Concentration of Contractive Stochastic Approximation and Reinforcement Learning. CoRR Siddharth Chandak, Vivek S. Borkar
2021	J	`jnl`	Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme. CoRR Konstantin Avrachenkov, Vivek S. Borkar, H. P. Dolhare, K. Patil
2021	—	`conf`	Linear and Dynamic Programs for Risk-Sensitive Cost Minimization. CDC Ari Arapostathis, Vivek S. Borkar
2021	J	`jnl`	Maximizing Conditional Entropy for Batch-Mode Active Learning of Perceptual Metrics. CoRR Priyadarshini Kumari, Siddhartha Chaudhuri, Vivek S. Borkar, Subhasis Chaudhuri
2021	J	`jnl`	Prospect-theoretic Q-learning. CoRR Vivek S. Borkar, Siddharth Chandak
2021	J	`jnl`	Prospect-theoretic Q-learning. Syst. Control. Lett. Vivek S. Borkar, Siddharth Chandak
2021	J	`jnl`	Scheduling in wireless networks with spatial reuse of spectrum as restless bandits. Perform. Evaluation Vivek S. Borkar, Shantanu Choudhary, Vaibhav Kumar Gupta, Gaurav S. Kasbekar
2021	J	`jnl`	The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning. CoRR Vivek S. Borkar, Shuhang Chen, Adithya M. Devraj, Ioannis Kontoyiannis, Sean P. Meyn
2021	J	`jnl`	User Association in Dense mmWave Networks as Restless Bandits. CoRR Santosh Kumar Singh, Vivek S. Borkar, Gaurav S. Kasbekar
2020	J	`jnl`	A Variational Characterization of the Risk-Sensitive Average Reward for Controlled Diffusions on ℝ SIAM J. Control. Optim. Ari Arapostathis, Anup Biswas, Vivek S. Borkar, K. Suresh Kumar
2020	J	`jnl`	Dynamic social learning under graph constraints. CoRR Konstantin Avrachenkov, Vivek S. Borkar, Sharayu Moharir, Suhail M. Shah
2020	J	`jnl`	Low Complexity Online Radio Access Technology Selection Algorithm in LTE-WiFi HetNet. IEEE Trans. Mob. Comput. Arghyadip Roy, Vivek S. Borkar, Prasanna Chaporkar, Abhay Karandikar
2020	J	`jnl`	Revisiting SIR in the age of COVID-19: Explicit Solutions and Control Problems. CoRR Vivek S. Borkar, D. Manjunath
2020	J	`jnl`	Whittle index based Q-learning for restless bandits with average reward. CoRR Konstantin Avrachenkov, Vivek S. Borkar
2019	—	`conf`	A Structure-aware Online Learning Algorithm for Markov Decision Processes. VALUETOOLS Arghyadip Roy, Vivek S. Borkar, Abhay Karandikar, Prasanna Chaporkar
2019	—	`conf`	A learning algorithm for the Whittle index policy for scheduling web crawlers. Allerton Konstantin Avrachenkov, Vivek S. Borkar
2019	J	`jnl`	Aerial monitoring of slow moving convoys using elliptical orbits. Eur. J. Control Aseem Vivek Borkar, Vivek S. Borkar, Arpita Sinha
2019	J	`jnl`	Average cost optimal control under weak hypotheses: Relative value iterations. CoRR Ari Arapostathis, Vivek S. Borkar
2019	J	`jnl`	LP Formulations of Discrete Time Long-Run Average Optimal Control Problems: The NonErgodic Case. SIAM J. Control. Optim. Vivek S. Borkar, Vladimir Gaitsgory, Ilya Shvartsman
2019	J	`jnl`	Linear Programming Formulation of Long-Run Average Optimal Control Problem. J. Optim. Theory Appl. Vivek S. Borkar, Vladimir Gaitsgory
2019	J	`jnl`	Metastability in Stochastic Replicator Dynamics. Dyn. Games Appl. Konstantin Avrachenkov, Vivek S. Borkar
2019	J	`jnl`	Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents. Math. Control. Signals Syst. Bhumesh Kumar, Vivek S. Borkar, Akhil Shetty
2019	—	`conf`	On LP Formulations of Optimal Control Problems with Time Averaging and Time Discounting Criteria in Non-Ergodic Case. CDC Vivek S. Borkar, Vladimir Gaitsgory, Ilya Shvartsman
2019	J	`jnl`	Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes. CoRR Arghyadip Roy, Vivek S. Borkar, Abhay Karandikar, Prasanna Chaporkar
2019	J	`jnl`	Opinion shaping in social networks using reinforcement learning. CoRR Vivek S. Borkar, Alexandre Reiffers-Masson
2019	J	`jnl`	Scheduling in Wireless Networks with Spatial Reuse of Spectrum as Restless Bandits. CoRR Vivek S. Borkar, Shantanu Choudhary, Vaibhav Kumar Gupta, Gaurav S. Kasbekar
2019	J	`jnl`	Stochastic approximation algorithms for rumor source inference on graphs. Perform. Evaluation Anand Kalvit, Vivek S. Borkar, Nikhil Karamchandani
2018	J	`jnl`	A Structure-aware Online Learning Algorithm for Markov Decision Processes. CoRR Arghyadip Roy, Vivek S. Borkar, Abhay Karandikar, Prasanna Chaporkar
2018	—	`conf`	Concentration bounds for two time scale stochastic approximation. Allerton Vivek S. Borkar, Sarath Pattathil
2018	Misc	`conf`	Distributed Algorithms: Tsitsiklis and Beyond. ITA Vivek S. Borkar, Suhail Mohmad Shah
2018	J	`jnl`	Distributed Stochastic Approximation with Local Projections. SIAM J. Optim. Suhail Mohmad Shah, Vivek S. Borkar
2018	J	`jnl`	Metastability in Stochastic Replicator Dynamics. CoRR Konstantin Avrachenkov, Vivek S. Borkar
2018	J	`jnl`	Opportunistic Scheduling as Restless Bandits. IEEE Trans. Control. Netw. Syst. Vivek S. Borkar, Gaurav S. Kasbekar, Sarath Pattathil, Priyesh Y. Shetty
2018	J	`jnl`	Q-learning for Markov decision processes with a satisfiability criterion. Syst. Control. Lett. Suhail M. Shah, Vivek S. Borkar
2018	J	`jnl`	Whittle Index Policy for Crawling Ephemeral Content. IEEE Trans. Control. Netw. Syst. Konstantin E. Avrachenkov, Vivek S. Borkar
2017	J	`jnl`	A Correction to "A Relative Value Iteration Algorithm for Nondegenerate Controlled Diffusions". SIAM J. Control. Optim. Ari Arapostathis, Vivek S. Borkar
2017	J	`jnl`	A Distributed Boyle-Dykstra-Han Scheme. SIAM J. Optim. Soham R. Phade, Vivek S. Borkar
2017	J	`jnl`	A Variational Formula for Risk-Sensitive Reward. SIAM J. Control. Optim. V. Anantharam, Vivek S. Borkar
2017	—	`conf`	A dynamic programming framework for optimal home scheduling. ISGT Asia Anupama Kowli, Joel Jose, Vivek S. Borkar, Imthias Ahamed T. P.
2017	J	`jnl`	Approachability in Stackelberg Stochastic Games with Vector Costs. Dyn. Games Appl. Dileep M. Kalathil, Vivek S. Borkar, Rahul Jain
2017	—	`conf`	Controlling G-AIMD by index policy. CDC Konstantin E. Avrachenkov, Vivek S. Borkar, Sarath Pattathil
2017	J	`jnl`	Distributed Reinforcement Learning via Gossip. IEEE Trans. Autom. Control. Adwaitvedant S. Mathkar, Vivek S. Borkar
2017	J	`jnl`	Distributed Server Allocation for Content Delivery Networks. CoRR Sarath Pattathil, Vivek S. Borkar, Gaurav S. Kasbekar
2017	J	`jnl`	Distributed Stochastic Approximation with Local Projections. CoRR Suhail M. Shah, Vivek S. Borkar
2017	J	`jnl`	Gradient Estimation with Simultaneous Perturbation and Compressive Sensing. J. Mach. Learn. Res. Vivek S. Borkar, Vikranth Reddy Dwaracherla, Neeraja Sahasrabudhe
2017	—	`conf`	Linear and dynamic programming approaches to degenerate risk-sensitive reward processes. CDC Vivek S. Borkar
2017	—	`conf`	MCMC Approaches to Rumor Source Inference using Pairwise Information. VALUETOOLS Anand Kalvit, Vivek S. Borkar, Nikhil Karamchandani
2017	J	`jnl`	Opportunistic Scheduling as Restless Bandits. CoRR Vivek S. Borkar, Gaurav S. Kasbekar, Sarath Pattathil, Priyesh Y. Shetty
2017	J	`jnl`	Temporally Agnostic Rumor-Source Detection. IEEE Trans. Signal Inf. Process. over Networks Ankit Kumar, Vivek S. Borkar, Nikhil Karamchandani
2017	J	`jnl`	Vector Field Guidance for Convoy Monitoring Using Elliptical Orbits. CoRR Aseem Vivek Borkar, Vivek S. Borkar, Arpita Sinha
2017	—	`conf`	Vector field guidance for convoy monitoring using elliptical orbits. CDC Aseem Vivek Borkar, Vivek S. Borkar, Arpita Sinha
2017	J	`jnl`	Whittle Index for Partially Observed Binary Markov Decision Processes. IEEE Trans. Autom. Control. Vivek S. Borkar
2017	J	`jnl`	Whittle Indexability in Egalitarian Processor Sharing Systems. CoRR Vivek S. Borkar, Sarath Pattathil
2016	Misc	`conf`	A concentration result for stochastic approximation (Extended abstract). ITA Gugan Thoppe, Vivek S. Borkar
2016	J	`jnl`	Actor-Critic Algorithms with Online Feature Adaptation. ACM Trans. Model. Comput. Simul. Prabuchandran K. J., Shalabh Bhatnagar, Vivek S. Borkar
2016	J	`jnl`	An Adaptive Window Scheme for Backoff in 802.11 MAC Protocol. EAI Endorsed Trans. Wirel. Spectr. Priyesh Y. Shetty, Vivek S. Borkar, Gaurav S. Kasbekar
2016	—	`conf`	Comparison of Random Walk Based Techniques for Estimating Network Averages. CSoNet Konstantin Avrachenkov, Vivek S. Borkar, Arun Kadavankandy, Jithin Kazuthuveettil Sreedharan
2016	C	`conf`	Distributed and Asynchronous Methods for Semi-supervised Learning. WAW Konstantin Avrachenkov, Vivek S. Borkar, Krishnakant V. Saboo
2016	—	`conf`	Edge conductance estimation using MCMC. Allerton Ashish Bora, Vivek S. Borkar, Dinesh Garg, Rajesh Sundaresan
2016	J	`jnl`	Fast rumor source identification via random walks. Soc. Netw. Anal. Min. Alankar Jain, Vivek S. Borkar, Dinesh Garg
2016	J	`jnl`	Gaussian approximations in high dimensional estimation. Syst. Control. Lett. Vivek S. Borkar, Raaz Dwivedi, Neeraja Sahasrabudhe
2016	J	`jnl`	Nonlinear Gossip. SIAM J. Control. Optim. Adwaitvedant S. Mathkar, Vivek S. Borkar
2016	J	`jnl`	Randomized Kaczmarz for Rank Aggregation from Pairwise Comparisons. CoRR Vivek S. Borkar, Nikhil Karamchandani, Sharad Mirani
2016	B	`conf`	Randomized Kaczmarz for rank aggregation from pairwise comparisons. ITW Vivek S. Borkar, Nikhil Karamchandani, Sharad Mirani
2015	J	`jnl`	Manufacturing Consent. IEEE Trans. Autom. Control. Vivek S. Borkar, Aditya Karnik, Jayakrishnan Nair, Sanketh Nalli
2015	J	`jnl`	Parallel and Distributed Approaches for Graph Based Semi-supervised Learning. CoRR Konstantin Avrachenkov, Vivek S. Borkar, Krishnakant V. Saboo
2015	Misc	`conf`	Rocking in two by two: From Collatz-Wielandt to Donsker-Varadhan. ITA V. Anantharam, Vivek S. Borkar
2015	J	`jnl`	Whittle Index Policy for Crawling Ephemeral Content. CoRR Konstantin Avrachenkov, Vivek S. Borkar
2015	—	`conf`	Whittle index policy for crawling ephemeral content. CDC Konstantin Avrachenkov, Vivek S. Borkar
2014	J	`jnl`	A Learning Scheme for Approachability in MDPs and Stackelberg Stochastic Games. CoRR Dileep M. Kalathil, Vivek S. Borkar, Rahul Jain
2014	J	`jnl`	A stochastic Kaczmarz algorithm for network tomography. Autom. Gugan Thoppe, Vivek S. Borkar, D. Manjunath
2014	J	`jnl`	An Improved Block Coordinate Descent Method for Quadratic Programming in High Dimensions. CoRR Gugan Thoppe, Vivek S. Borkar, Dinesh Garg
2014	—	`conf`	An actor critic algorithm based on Grassmanian search. CDC Prabuchandran K. J., Shalabh Bhatnagar, Vivek S. Borkar
2014	J	`jnl`	Asynchronous Gossip for Averaging and Spectral Ranking. IEEE J. Sel. Top. Signal Process. Vivek S. Borkar, Rahul Makhijani, Rajesh Sundaresan
2014	—	`conf`	Blackwell's approachability in stackelberg stochastic games: A learning version. CDC Dileep M. Kalathil, Vivek S. Borkar, Rahul Jain
2014	J	`jnl`	Convergence of the Relative Value Iteration for the Ergodic Control Problem of Nondegenerate Diffusions under Near-Monotone Costs. SIAM J. Control. Optim. Ari Arapostathis, Vivek S. Borkar, K. Suresh Kumar
2014	J	`jnl`	Empirical Q-Value Iteration. CoRR Dileep M. Kalathil, Vivek S. Borkar, Rahul Jain
2014	—	`conf`	From Collatz-Weilandt to Donkser-Varadhan via Krein-Rutman. CDC Ari Arapostathis, Vivek S. Borkar, K. Suresh Kumar
2014	Misc	`conf`	Reinforcement Learning for Matrix Computations: PageRank as an Example. ICDCIT Vivek S. Borkar, Adwaitvedant S. Mathkar
2014	Misc	`conf`	Reinforcement learning, particle filters and the EM algorithm. ITA Vivek S. Borkar, Ankushkumar Jain
2014	J	`jnl`	Risk-Constrained Markov Decision Processes. IEEE Trans. Autom. Control. Vivek S. Borkar, Rahul Jain
2014	—	`conf`	Stabilization of a quasi-linear parabolic Cauchy problem associated with ergodic control of diffusions. CDC Ari Arapostathis, Vivek S. Borkar, K. Suresh Kumar
2014	A	`conf`	Submodularity in Team Formation Problem. SDM Avradeep Bhowmik, Vivek S. Borkar, Dinesh Garg, Madhavan Pallan
2013	J	`jnl`	Convergence of The Relative Value Iteration for the Ergodic Control Problem of Nondegenerate Diffusions under Near-Monotone Costs CoRR Ari Arapostathis, Vivek S. Borkar, K. Suresh Kumar
2013	J	`jnl`	Distributed Reinforcement Learning via Gossip. CoRR Adwaitvedant S. Mathkar, Vivek S. Borkar
2013	J	`jnl`	Feature Search in the Grassmanian in Online Reinforcement Learning. IEEE J. Sel. Top. Signal Process. Shalabh Bhatnagar, Vivek S. Borkar, Prabuchandran K. J.
2013	Misc	`conf`	Gossip with transmission constraints. ITA Vivek S. Borkar, Rahul Makhijani, Rajesh Sundaresan
2013	J	`jnl`	How to gossip if you must. CoRR Vivek S. Borkar, Rahul Makhijani, Rajesh Sundaresan
2013	J	`jnl`	Markov chains, Hamiltonian cycles and volumes of convex bodies. J. Glob. Optim. Vivek S. Borkar, Jerzy A. Filar
2013	J	`jnl`	Model-based clock synchronization protocol for wireless sensor networks. CoRR Nikolaos M. Freris, Vivek S. Borkar, P. R. Kumar
2013	J	`jnl`	On the diffusion of messages in on-line social networks. Perform. Evaluation Aditya Karnik, Atul Saroop, Vivek S. Borkar
2013	J	`jnl`	Reinforcement Learning for Matrix Computations: PageRank as an Example. CoRR Vivek S. Borkar, Adwaitvedant S. Mathkar
2012	J	`jnl`	A Relative Value Iteration Algorithm for Nondegenerate Controlled Diffusions. SIAM J. Control. Optim. Ari Arapostathis, Vivek S. Borkar
2012	—	`conf`	A relative value iteration for controlled diffusions under ergodic cost. CDC Ari Arapostathis, Vivek S. Borkar
2012	J	`jnl`	Oja's algorithm for graph clustering, Markov spectral decomposition, and risk sensitive control. Autom. Vivek S. Borkar, Sean P. Meyn
2012	J	`jnl`	Relative Value Iteration for Stochastic Differential Games CoRR Ari Arapostathis, Vivek S. Borkar, K. Suresh Kumar
2012	J	`jnl`	Stochastic approximation with long range dependent and heavy tailed noise. Queueing Syst. Theory Appl. Venkat Anantharam, Vivek S. Borkar
2012	—	`conf`	Who is the fairest of them all? Allerton Conference Vivek S. Borkar, Rahul M. Makhijani
2011	J	`jnl`	Asymptotics of the Invariant Measure in Mean Field Models with Jumps CoRR Vivek S. Borkar, Rajesh Sundaresan
2011	—	`conf`	Controlled gossip. Allerton Vivek S. Borkar, Aditya Karnik
2011	—	`conf`	Convergence analysis for an online recommendation system. CDC/ECC Anh Truong, Negar Kiyavash, Vivek S. Borkar
2011	J	`jnl`	Optimal Control of Sleep Periods for Wireless Terminals. IEEE J. Sel. Areas Commun. Amar Prakash Azad, Sara Alouf, Eitan Altman, Vivek S. Borkar, Georgios S. Paschos
2011	A*	`conf`	Risk sensitive optimal control framework applied to delay tolerant networks. INFOCOM Eitan Altman, Veeraruna Kavitha, Francesco De Pellegrini, Vijay Kamble, Vivek S. Borkar
2011	Misc	`conf`	Stochastic approximation with 'bad' noise. ITA Venkat Anantharam, Vivek S. Borkar
2010	J	`jnl`	A Stable Online Algorithm for Energy-Efficient Multiuser Scheduling. IEEE Trans. Mob. Comput. Nitin Salodkar, Abhay Karandikar, Vivek S. Borkar
2010	J	`jnl`	Application of nonlinear filtering to credit risk. Oper. Res. Lett. Vivek S. Borkar, Mrinal K. Ghosh, Govindan Rangarajan
2010	J	`jnl`	ERRATUM: White-Noise Representations in Stochastic Realization Theory. SIAM J. Control. Optim. Vivek S. Borkar
2010	—	`conf`	Manufacturing consent. Allerton Vivek S. Borkar, Jayakrishnan Nair, Sanketh Nalli
2010	J	`jnl`	On a controlled eigenvalue problem. Syst. Control. Lett. Anup Biswas, Vivek S. Borkar
2010	J	`jnl`	Quasi-stationary distributions as centrality measures for the giant strongly connected component of a reducible graph. J. Comput. Appl. Math. Konstantin Avrachenkov, Vivek S. Borkar, Danil Nemirovsky
2010	—	`conf`	Risk-constrained Markov decision processes. CDC Vivek S. Borkar, Rahul Jain
2010	J	`jnl`	Singular Perturbations in Risk-Sensitive Stochastic Control. SIAM J. Control. Optim. Vivek S. Borkar, K. Suresh Kumar
2010	J	`jnl`	Uniform Recurrence Properties of Controlled Diffusions and Applications to Optimal Control. SIAM J. Control. Optim. Ari Arapostathis, Vivek S. Borkar
2009	J	`jnl`	A New Learning Algorithm for Optimal Stopping. Discret. Event Dyn. Syst. Vivek S. Borkar, Jervis Pinto, Tarun Prabhu
2009	J	`jnl`	A Stable On-line Algorithm for Energy Efficient Multi-user Scheduling CoRR Nitin Salodkar, Abhay Karandikar, Vivek S. Borkar
2009	A*	`conf`	A Theory of QoS for Wireless. INFOCOM I-Hong Hou, Vivek S. Borkar, P. R. Kumar
2009	—	`conf`	A model-based approach to clock synchronization. CDC Nikolaos M. Freris, Vivek S. Borkar, P. R. Kumar
2009	J	`jnl`	A novel ACO algorithm for optimization via reinforcement and initial bias. Swarm Intell. Vivek S. Borkar, Dibyajyoti Das
2009	—	`conf`	Convergence of population dynamics in symmetric routing games with a finite number of playersz. GAMENETS Eitan Altman, Vijay Kamble, Vivek S. Borkar
2009	J	`jnl`	Cooperative dynamics and Wardrop equilibria. Syst. Control. Lett. Vivek S. Borkar
2009	J	`jnl`	Finite dimensional approximation and Newton-based algorithm for stochastic approximation in Hilbert space. Autom. Ankur A. Kulkarni, Vivek S. Borkar
2009	J	`jnl`	On the Hamiltonicity Gap and doubly stochastic matrices. Random Struct. Algorithms Vivek S. Borkar, Vladimir Ejov, Jerzy A. Filar
2009	—	`conf`	Optimal sampling for state change detection with application to the control of sleep mode. CDC Amar Prakash Azad, Sara Alouf, Eitan Altman, Vivek S. Borkar, George Paschos
2009	—	`conf`	Vacation policy optimization with application to IEEE 802.16e power saving mechanism. Wireless Days Amar P. Azad, Sara Alouf, Eitan Altman, Vivek S. Borkar, Georgios S. Paschos
2008	J	`jnl`	A Learning Algorithm for Risk-Sensitive Cost. Math. Oper. Res. Arnab Basu, Tirthankar Bhattacharyya, Vivek S. Borkar
2008	—	`conf`	A learning scheme for stationary probabilities of large markov chains with examples. Allerton Vivek S. Borkar, D. J. Das, Abhijit Datta Banik, D. Manjunath
2008	J	`jnl`	A note on linear function approximation using random projections. Syst. Control. Lett. Kishor Barman, Vivek S. Borkar
2008	J	`jnl`	An on-line learning algorithm for energy efficient delay constrained scheduling over a fading channel. IEEE J. Sel. Areas Commun. Nitin Salodkar, Abhijeet Bhorkar, Abhay Karandikar, Vivek S. Borkar
2008	J	`jnl`	Distributed topology control of wireless networks. Wirel. Networks Vivek S. Borkar, D. Manjunath
2008	A*	`conf`	Index Policies for Real-Time Multicast Scheduling for Wireless Broadcast Systems. INFOCOM Vivek Raghunathan, Vivek S. Borkar, Min Cao, P. R. Kumar
2008	—	`conf`	Oja's algorithm for graph clustering and Markov spectral decomposition. VALUETOOLS Vivek S. Borkar, Sean P. Meyn
2008	—	`conf`	Opportunistic Transmission over Randomly Varying Channels. NET-COOP Vivek S. Borkar
2008	J	`jnl`	Stochastic Control with Imperfect Models. SIAM J. Control. Optim. Arnab Basu, Vivek S. Borkar
2008	J	`jnl`	Structural Properties of Optimal Transmission Policies Over a Randomly Varying Channel. IEEE Trans. Autom. Control. Mukul Agarwal, Vivek S. Borkar, Abhay Karandikar
2007	B	`conf`	An Information Theoretic View of Stochastic Resonance. ISIT Venkat Anantharam, Vivek S. Borkar
2007	J	`jnl`	Common randomness and distributed control: A counterexample. Syst. Control. Lett. Venkat Anantharam, Vivek S. Borkar
2007	J	`jnl`	Dynamic Programming for Ergodic Control of Markov Chains under Partial Observations: A Correction. SIAM J. Control. Optim. Vivek S. Borkar
2007	J	`jnl`	Power Efficient Scheduling under Delay Constraints over Multi-user Wireless Channels CoRR Nitin Salodkar, Abhay Karandikar, Vivek S. Borkar
2007	J	`jnl`	Quasi-stationary distributions as centrality measures of reducible graphs CoRR Konstantin Avrachenkov, Vivek S. Borkar, Danil Nemirovsky
2007	J	`jnl`	Singular Perturbations in Ergodic Control of Diffusions. SIAM J. Control. Optim. Vivek S. Borkar, Vladimir Gaitsgory
2007	—	`conf`	Some Examples of Stochastic Approximation in Communications. NET-COOP Vivek S. Borkar
2006	—	`conf`	A New Distributed Time Synchronization Protocol for Multihop Wireless Networks. CDC Roberto Solis-Robles, Vivek S. Borkar, Panganamala R. Kumar
2006	J	`jnl`	A Simulation-Based Algorithm for Ergodic Control of Markov Chains Conditioned on Rare Events. J. Mach. Learn. Res. Shalabh Bhatnagar, Vivek S. Borkar, Madhukar Akarapu
2006	J	`jnl`	Adaptive Importance Sampling Technique for Markov Chains Using Stochastic Approximation. Oper. Res. T. P. I. Ahamed, Vivek S. Borkar, S. Juneja
2006	J	`jnl`	Distributed self-tuning of sensor networks. Wirel. Networks Aditya Karnik, Anurag Kumar, Vivek S. Borkar
2006	J	`jnl`	Erratum to "Avoidance of traps in stochastic approximation" [Systems Control Letters 50 (2003) 1-9]. Syst. Control. Lett. Vivek S. Borkar
2006	—	`conf`	Existence of limit occupational measures set used for averaging of singularly perturbed controlled stochastic differential equations. CDC Vivek S. Borkar, Vladimir Gaitsgory
2006	B	`conf`	Power Optimal Opportunistic Scheduling. GLOBECOM Abhijeet Bhorkar, Abhay Karandikar, Vivek S. Borkar
2006	J	`jnl`	Stochastic approximation with 'controlled Markov' noise. Syst. Control. Lett. Vivek S. Borkar
2005	J	`jnl`	An actor-critic algorithm for constrained Markov decision processes. Syst. Control. Lett. Vivek S. Borkar
2005	B	`conf`	Closed and Open Loop Optimal Control of Buffer and Energy of a Wireless Device. WiOpt Vivek S. Borkar, Arzad Alam Kherani, B. J. Prabhu
2005	B	`conf`	Distributed Topology Control of Wireless Networks. WiOpt Vivek S. Borkar, D. Manjunath
2005	—	`conf`	HJB Equations for Ergodic Control Problems for Constrained Diffusions in Polyhedral Domains. CDC/ECC Vivek S. Borkar, Amarjit Budhiraja
2005	J	`jnl`	On Existence of Limit Occupational Measures Set of a Controlled Stochastic Differential Equation. SIAM J. Control. Optim. Vivek S. Borkar, Vladimir Gaitsgory
2005	—	`conf`	Sequential Source Coding: An optimization viewpoint. CDC/ECC Vivek S. Borkar, Sanjoy K. Mitter, Anant Sahai, Sekhar Tatikonda
2004	J	`jnl`	Charge-based control of DiffServ-like queues. Autom. Vivek S. Borkar, D. Manjunath
2004	J	`jnl`	Directed graphs, Hamiltonicity and doubly stochastic matrices. Random Struct. Algorithms Vivek S. Borkar, Vladimir Ejov, Jerzy A. Filar
2004	J	`jnl`	Ergodic Control for Constrained Diffusions: Characterization Using HJB Equations. SIAM J. Control. Optim. Vivek S. Borkar, Amarjit Budhiraja
2004	B	`conf`	Optimal random access in networks with two-way traffic. PIMRC Eitan Altman, Vivek S. Borkar, Arzad Alam Kherani
2004	—	`conf`	Some Game-Theoretic Problems in Wireless Ad-Hoc Networks. EuroNGI Workshop Eitan Altman, Vivek S. Borkar, Arzad Alam Kherani, Pietro Michiardi, Refik Molva
2003	—	`conf`	Algorithmic Mechanisms for Secure Multi-Auction Systems. IICAI Vivek S. Borkar, Mehul S. Dave, R. K. Shyamasundar
2003	J	`jnl`	Avoidance of traps in stochastic approximation. Syst. Control. Lett. Vivek S. Borkar
2003	J	`jnl`	Dynamic Cesaro-Wardrop equilibration in networks. IEEE Trans. Autom. Control. Vivek S. Borkar, Panganamala Ramana Kumar
2003	J	`jnl`	Multiscale Chaotic SPSA and Smoothed Functional Algorithms for Simulation Optimization. Simul. Shalabh Bhatnagar, Vivek S. Borkar
2003	J	`jnl`	Peformance Analysis Conditioned on Rare Events: An Adaptive Simulation Scheme. Commun. Inf. Syst. Vivek S. Borkar, S. Juneja, Arzad Alam Kherani
2003	—	`conf`	Value functions and performance evaluation in stochastic network models. CDC Vivek S. Borkar, Sean P. Meyn
2002	A*	`conf`	Differential Join Prices for Parallel Queues: Social Optimality, Dynamic Pricing Algorithms and Application to Internet Pricing. INFOCOM Parijat Dube, Vivek S. Borkar, D. Manjunath
2002	J	`jnl`	Mathematical Programming Embeddings of Logic. J. Autom. Reason. Vivek S. Borkar, Vijay Chandru, Sanjoy K. Mitter
2002	J	`jnl`	On The Lock-In Probability Of Stochastic Approximation. Comb. Probab. Comput. Vivek S. Borkar
2002	J	`jnl`	Q-Learning for Risk-Sensitive Control. Math. Oper. Res. Vivek S. Borkar
2002	J	`jnl`	Reinforcement Learning in Markovian Evolutionary Games. Adv. Complex Syst. Vivek S. Borkar
2002	J	`jnl`	Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost. Math. Oper. Res. Vivek S. Borkar, Sean P. Meyn
2002	J	`jnl`	Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms. SIAM J. Control. Optim. Jinane Abounadi, Dimitri P. Bertsekas, Vivek S. Borkar
2001	J	`jnl`	A sensitivity formula for risk-sensitive cost and the actor-critic algorithm. Syst. Control. Lett. Vivek S. Borkar
2001	J	`jnl`	Learning Algorithms for Markov Decision Processes with Average Cost. SIAM J. Control. Optim. Jinane Abounadi, Dimitri P. Bertsekas, Vivek S. Borkar
2001	J	`jnl`	Markov control problems under communication constraints. Commun. Inf. Syst. Vivek S. Borkar, Sanjoy K. Mitter, Sekhar Tatikonda
2001	J	`jnl`	Optimal Sequential Vector Quantization of Markov Sources. SIAM J. Control. Optim. Vivek S. Borkar, Sanjoy K. Mitter, Sekhar Tatikonda
2001	—	`conf`	Optimal sequential vector quantization of Markov sources. CDC Vivek S. Borkar, Sanjoy K. Mitter, Sekhar Tatikonda
2000	—	`conf`	A learning algorithm for Markov decision processes with adaptive state aggregation. CDC John S. Baras, Vivek S. Borkar
2000	J	`jnl`	Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations. SIAM J. Control. Optim. Vivek S. Borkar
2000	J	`jnl`	Erratum: Asynchronous Stochastic Approximations. SIAM J. Control. Optim. Vivek S. Borkar
2000	J	`jnl`	The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning. SIAM J. Control. Optim. Vivek S. Borkar, Sean P. Meyn
1999	J	`jnl`	Actor-Critic - Type Learning Algorithms for Markov Decision Processes. SIAM J. Control. Optim. Vijaymohan Konda, Vivek S. Borkar
1999	J	`jnl`	Randomized neural networks for learning stochastic dependences. IEEE Trans. Syst. Man Cybern. Part B Vivek S. Borkar, Piyush Gupta
1998	J	`jnl`	A unified framework for hybrid control: model and optimal control theory. IEEE Trans. Autom. Control. Michael S. Branicky, Vivek S. Borkar, Sanjoy K. Mitter
1998	J	`jnl`	Dynamics of individual specialization and global diversification in communities. Complex. Vivek S. Borkar, Sanjay Jain, Govindan Rangarajan
1998	J	`jnl`	Generalized Replicator Dynamics as a Model of Specialization and Diversity in Societies. Adv. Complex Syst. Vivek S. Borkar, Sanjay Jain, Govindan Rangarajan
1997	J	`jnl`	Learning Decentralized Goal-based Vector Quantization. Complex Syst. Piyush Gupta, Vivek S. Borkar
1996	J	`jnl`	Stochastic processes that generate polygonal and related random fields. IEEE Trans. Inf. Theory Vivek S. Borkar, Sanjoy K. Mitter
1995	J	`jnl`	A Convex Analytic Framework for Ergodic Control of Semi-Markov Processes. Math. Oper. Res. Shalabh Bhatnagar, Vivek S. Borkar
1995	—	`conf`	Epsilon-Approximation of Differential Inclusions. Hybrid Systems Anuj Puri, Vivek S. Borkar, Pravin Varaiya
1992	J	`jnl`	Ergodic and adaptive control of nearest-neighbor motions. Math. Control. Signals Syst. Vivek S. Borkar, Mrinal K. Ghosh
1992	J	`jnl`	Weak convergence methods and singularly perturbed stochastic control and filtering problems: Harold J. Kushner. Autom. Vivek S. Borkar
1991	J	`jnl`	A remark on control of partially observed Markov chains. Ann. Oper. Res. Vivek S. Borkar
1991	J	`jnl`	Ergodic and adaptive control of nearest-neighbor motions. Math. Control. Signals Syst. Vivek S. Borkar, Mrinal K. Ghosh