Publications
[Preprints]
[J28] A. S. Bedi*, C. Fan*, A. Koppel, A. K. Sahu, B. M. Sadler, F. Huang, and D. Manocha , "FedBC: Calibrating Global and Local Models via Federated Learning Beyond Consensus ", May, 2022.
[J27] A. Koppel*, A. S. Bedi*, B. Ganguly, and V. Aggarwal, "Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programming", submitted to IEEE Transactions on Networking, Mar 2022.
[J26] A. S. Bedi, A. Koppel, K. Rajawat, and Brian M. Sadler, "Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony," in IEEE Transactions on Signal Processing (submitted), Aug. 2019.
[Journals]
[J25] A. S. Bedi, A. Parayil, J. Zhang, M. Wang, and A. Koppel , "On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control" in Journal of Machine Learning Research (JMLR), Jan 2024.
[J24] A. S. Bedi, D. Peddireddy, V. Aggarwal, and A. Koppel, "Efficient Gaussian Process Bandits by Believing only Informative Actions," in IEEE Transactions on Artificial Intelligence (TAI), Sep. 2023.
[J23] Q. Bai, A. S. Bedi, M. Agarwal, A. Koppel, and V. Aggarwal, "Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach", in Journal of Artificial Intelligence Research (JAIR), Nov, 2023.
[J22] Z. Akhtar, A. S. Bedi, S. T. Thomdapu, K. Rajawat , "Projection-Free Algorithm for Stochastic Bi-level Optimization", in IEEE Transactions on Signal Processing (TSP), Nov. 2022.
[J21] A. S. Bedi, K. Rajawat, V. Aggarwal and A. Koppel, "Escaping Saddle Points with the Successive Convex Approximation Algorithm," in IEEE Transactions on Signal Processing (TSP), Nov. 2021.
[J20] A. Koppel*, A. S. Bedi*, B. M. Sadler, and V. Elvira, "Approximate Shannon Sampling in Importance Sampling: Nearly Consistent Finite Particle Estimates," in IEEE Transactions on Signal Processing (TSP), Sep. 2021.
[J19] J. Zhang*, A. S. Bedi*, M. Wang and A. Koppel, "Cautious Reinforcement Learning via Distributional Risk in the Dual Domain," in IEEE Journal on Selected Areas in Information Theory (JSAIT), vol. 2, no. 2, pp. 611-626, June 2021.
[J18] Z. Akhtar, A. S. Bedi, and K. Rajawat, "Conservative Stochastic Optimization with Expectation Constraints ," in IEEE Transactions on Signal Processing (TSP), vol. 69, pp. 3190-3205, May 2021.
[J17] H. Pradhan, A. S. Bedi, A. Koppel, and K. Rajawat, "Adaptive Kernel Learning in Heterogeneous Networks," in IEEE Transactions on Signal and Information Processing (TSIPN), Feb. 2021.
[J16] Deepak Kalhan, A. S. Bedi, A. Koppel, K. Rajawat, H. Hassani, A. Gupta, and A. Banerjee, "Dynamic Online Learning via Frank-Wolfe Algorithm," in IEEE Transactions on Signal Processing (TSP), Dec. 2020.
[J15] R. Dixit, A. S. Bedi, and K. Rajawat, "Online Learning over Dynamic Graphs via Distributed Proximal Gradient Algorithm," in IEEE Transactions on Automatic Control (TAC), Nov. 2021.
[J14] A. Elgabli, J. Park, A. S. Bedi, Chaouki Ben Issaid, M. Bennis, and V. Aggarwal,, "Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning," in IEEE Transaction on Communications (TCOM), Sep. 2020.
[J13] Y. Tian, A. Koppel, A. S. Bedi, and J. How, “Asynchronous and Parallel Distributed Pose Graph Optimization,” in IEEE Robotics and Automation Letters (RAL), Feb. 2020. [2020 Honorable Mention from IEEE Robotics and Automation Letters ]
[J12] A. Elgabli, J. Park, A. S. Bedi, M. Bennis, and V. Aggarwal,, "GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning," in Journal of Machine Learning and Research (JMLR), Mar., 2020.
[J11] A. Koppel, A. S. Bedi, K, Rajawat, and B. M. Sadler, "Optimally Compressed Nonparametric Online Learning," in IEEE Signal Processing Magazine - Special Issue on Distributed, Streaming Machine Learning (SPM), May 2020.
[J10] M. Krishna, A. S. Bedi, K. Rajawat, and M. Coupechoux "Online Trajectory Optimization Using Inexact Gradient Feedback for Time-Varying Environments ," in IEEE Transactions on Signal Processing (TSP), July. 2020.
[J9] A. S. Bedi, A. Koppel, K. Rajawat, and Panchajanya Sanyal , "Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning," in IEEE Transactions on Signal Processing (TSP), Dec. 2020.
[J8] A. S. Bedi, A. Koppel, and K. Rajawat, "Asynchronous Online Learning in Multi-Agent Systems with Proximity Constraints," in IEEE Transactions on Signal and Information Processing over Networks (TSIPN), vol. 5, no. 3, pp. 479-494, Sept. 2019.
[J7] R. Dixit, A. S. Bedi, R. Tripathi, and K. Rajawat, "Online Learning with Inexact Proximal Online Gradient Descent Algorithms," in IEEE Transactions on Signal Processing (TSP), vol. 67, no. 5, pp. 1338-1352, Mar. 2019.
[J6] A. S. Bedi, A. Koppel, and K. Rajawat, "Asynchronous Saddle Point Algorithm for Stochastic Optimization in Heterogeneous Networks," in IEEE Transactions on Signal Processing (TSP), vol. 67, no. 7, pp. 1742-1757, Apr. 2019.
[J5] A. S. Bedi and K. Rajawat, "Asynchronous Incremental Stochastic Dual Descent Algorithm for Network Resource Allocation," in IEEE Transactions on Signal Processing (TSP), vol. 66, no. 9, pp. 2229-2244, May 1, 2018.
[J4] A. S. Bedi, P V Aditya Prasad, Md. Waseem Ahmad, Swapnil Shinde, Ketan Rajawat, and Sandeep Anand, "Online Algorithms for Storage Utilization under Real-Time Pricing in Smart Grid," International Journal of Electrical Power and Energy Systems (JEPES), vol 101, Mar. 2018.
[J3] A. S. Bedi, P. Sarma, and K. Rajawat, " Tracking Moving Agents via Inexact Online Gradient Descent Algorithm," in IEEE Journal of Selected Topics in Signal Processing - Special issue on Machine Learning for Cognition in Radio Communications and Radar (JSTSP), vol. 12, no. 1, pp. 202-217, Feb. 2018..
[J2] A. S. Bedi and K. Rajawat, "Network Resource Allocation via Stochastic Subgradient Descent: Convergence Rate ," in IEEE Transactions on Communications (TCOM), vol. 66, no. 5, pp. 2107-2121, May 2018.
[J1] A. S. Bedi, J. Akhtar, K. Rajawat, and A. K. Jagannatham, "BER-Optimized Precoders for OFDM systems with Insufficient Cyclic Prefix," in IEEE Communication Letters, vol. 20, no. 2, pp 280-283, Feb. 2016.
[Conferences]
[C54] S. Chakraborty, A. S. Bedi, A. Koppel, D. Manocha, H. Wang, M. Wang, and F. Huang, "PARL: A Unified Framework for Policy Alignment in Reinforcement Learning", in International Conference on Learning Representations (ICLR), Vienna, Austria, May 2024.
[C53] X. Wu, R. Chandra, T. Guan, A. S. Bedi, and D. Manocha, ''iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning", in Conference on Robotic Learning (CORL), Atlanta, GA, USA, Nov 2023. [Oral]
[C52] H.J. He, A. Koppel, A. S. Bedi, M. Farhood, and D. J. Stilwell, ``Bi-Level Nonstationary Kernels for Online Gaussian Process Regression," in IEEE 19th International Conference on Automation Science and Engineering (CASE), 2023.
[C51] S. Chakraborty, A. S. Bedi, A. Koppel, M. Wang, F. Huang, D. Manocha, "STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning", in International Conference on Machine Learning (ICML), Honolulu, Hawai, USA, July 2023.
[C50] A. S. Bedi*, W. Suttle*, B. Patel, B. Sadler, A. Koppel, D. Manocha, "Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic", in International Conference on Machine Learning (ICML), Honolulu, Hawai, USA, July 2023.
[C49] M. Bornstein, T. Rabbani, E. Wang, A. S. Bedi, and F. Huang , "SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication ", in International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023.
[C48] S.Chakraborty, A. S. Bedi, K. Weerakoon, P. Poddar, A. Koppel, P. Tokekar, and D. Manocha, "Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization ", in International Conference on Robotics (ICRA), London, UK, May 2023.
[C47] A. Aggarwal, A. S. Bedi, and D. Manocha, "RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments", in International Conference on Robotics (ICRA), London, UK, May 2023.
[C46] H. He, A. Koppel, A. S. Bedi, D. Stilwell, and M. Farhood, "Decentralized Multi-agent Exploration with Limited Inter-agent Communications", in International Conference on Robotics (ICRA), London, UK, May 2023.
[C45] Q. Bai, A. S. Bedi, and V. Aggarwal, "Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm", in AAAI Conference on Artificial Intelligence, Washington DC, USA, Feb 2023.
[C44] S.Chakraborty, A. S. Bedi, A. Koppel, B. Sadler, F. Huang, P. Tokekar, and D. Manocha , "Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning", in AAAI Conference on Artificial Intelligence, Washington DC, USA, Feb 2023.
[C43] A. Koppel*, A. S. Bedi*, B. Ganguly, and V. Aggarwal, "Convergence Rates of Average-Reward Multi-Agent Reinforcement Learning Via Randomized Linear Programming," in Proc. of the IEEE Conf. on Decision and Control (CDC), Cancun, Mexico, Dec. 2022.
[C42] K. Weerakoon, S. Chakraborty, N. Karapetyan, A. J. Sathyamoorthy, A. S. Bedi and D. Manocha , "HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm", in Proc. of the Conference on Robotic Learning (CoRL), Aukland, New Zeland, 2022.
[C41] K. Chakrabarti, A. S. Bedi, F. T. Dagefu, J. N. Twigg, and N. Chopra, "Fast Distributed Beamforming without Receiver Feedback ", in Proc. of the 56th Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2022.
[C40] Y. Tian, A. S. Bedi, A. Koppel, M. C. Fullana, D. Rosen, and J. How, "Distributed Riemannian Optimization with Lazy Communication for Collaborative Geometric Estimation", in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, Oct. 2022.
[C39] A. Agrawal, S. H. Arul, A. S. Bedi, and D. Manocha , "DC-MRTA: Decentralized Multi-Robot Task Allocation and Navigation in Complex Environments", in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, Oct. 2022.
[C38] A. Elgabli, C. B. Issaid, A. S. Bedi, K. Rajawat, M. Bennis, and V. Aggarwal, "FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning", in International Conference on Machine Learning (ICML), Baltimore, USA, July 2022.
[C37] A. S. Bedi, S. Chakraborty, A Parayil, B. Sadler, P. Tokekar, and A. Koppel, "On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces", in International Conference on Machine Learning (ICML), Baltimore, USA, July 2022.
[C36] Q. Bai, A. S. Bedi, M. Agarwal, A. Koppel, and V. Aggarwal, "Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach", in AAAI Conference on Artificial Intelligence, Vancouver, Canada, Feb 2022.
[C35] J. Zhang, A. S. Bedi, M. Wang, and A. Koppel, "MARL with General Utilities via Decentralized Shadow Reward Actor-Critic" in AAAI Conference on Artificial Intelligence, Vancouver, Canada, Feb 2022.
[C34] A. Elgabli, C. B. Issaid, A. S. Bedi, M. Bennis, V. Aggarwal, "Energy-Efficient and Federated Meta-Learning via Projected Stochastic Gradient Ascent", in Proc. of IEEE Globecom, Madrid, Spain, Dec. 2021.
[C33] A. Koppel, A. S. Bedi, B. Ganguly, and V. Aggarwal, "Randomized Linear Programming for Tabular Average-Cost Multi-agent Reinforcement Learning ," in Proc. 55th Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2021.
[C32] A. S. Bedi, A. Koppel, M. Wang, and J. Zhang, "Intermittent Communications in Decentralized Shadow Reward Actor-Critic", in Proc. of the IEEE Conf. on Decision and Control (CDC), Nice, France, Dec. 2021.
[C31] M. E. Kepler, A. Koppel, A. S. Bedi, and D. J. Stilwell, "Wasserstein-Splitting Gaussian Process Regression for Heterogeneous Online Bayesian Inference", in IROS, 2021.
[C30] A. Koppel, A. S. Bedi, and V. Krishnamurthy, "On the Convergence Theory of Online Bayesian Nonparametric Estimators with Adaptive Hyperparameters", in ICASSP, 2021.
[C29] J. Zhang, A. Koppel, A. S. Bedi, C. Szepesvari, and M. Wang, "Variational Policy Gradient Method for Reinforcement Learning with General Utilities," in Advances in Neural Information Processing Systems (NIPS), Vancouver, CA, 6-12 Dec., 2020. [Spotlight (Top 4% of submitted papers) ]
[C28] A. Parayil, A. S. Bedi, A. Koppel, "Joint Position and Beamforming Control via Alternating Nonlinear Least-Squares with a Hierarchical Gamma Prior", in American Control Conference (ACC), 2021.
[C27] J Zhang*, A. S. Bedi*, M. Wang, and A. Koppel, "Beyond Cumulative Returns via Reinforcement Learning over State-Action Occupancy Measures", in American Control Conference (ACC), 2021.
[C26] Z Akhtar, A. S. Bedi, and K. Rajawat, "Conservative Stochastic Optimization: O(T^(-1/2)) Optimality Gap with Zero Constraint Violation ", in American Control Conference (ACC), 2021.
[C25] H. Pradhan, A. S. Bedi, A. Koppel, and K. Rajawat, "Conservative Multi-agent Online Kernel Learning in Heterogeneous Networks ," in Proc. 54th Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2020.
[C24] Y. Tian, A. Koppel, A. S. Bedi, and J. How, “Asynchronous and Parallel Distributed Pose Graph Optimization,” in International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, Oct. 2020.
[C23] A. S. Bedi, D. Peddireddy, V. Aggarwal, and A. Koppel, "Efficient Large-Scale Gaussian Process Bandits by Believing only Informative Actions ," in Learning for Dynamics and Control (L4DC), University of California, Berkeley, CA , June 2020.
[C22] A. Koppel*, A. S. Bedi*, B. M. Sadler, and V. Elvira, "A Projection Operator to Balance Consistency and Complexity in Importance Sampling," in NeurIPS Symposium on Advances in Approximate Bayesian Inference (to appear), Vancouver, CA, Dec. 14, 2019. [*Equal contribution]
[C21] Deepak Kalhan, A. S. Bedi, A. Koppel, K. Rajawat, A. Gupta, and A. Banerjee, "Projection Free Dynamic Online Learning," in Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP), Barcelona, Spain, May 4-8, 2020 (submitted).
[C20] A. Elgabli, J. Park, A. S. Bedi, M. Bennis, and V. Aggarwal,, "Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning," in Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP), Barcelona, Spain, May 4-8, 2020 (submitted).
[C19] A. S. Bedi, A. Koppel, K. Rajawat, and Brian M. Sadler, "Nonparametric Dynamic Online Learning," in IEEE American Control Conference (ACC), Denver, CO, USA, Jul. 1-3, 2020.
[C18] A. S. Bedi, A. Koppel, B. M. Sadler, and V. Elvira, " Approximate Shannon Sampling in Importance Sampling ," in Proc. 53rd Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2019.
[C17] A. S. Bedi, A. Koppel, and K. Rajawat, "Nonstationary Nonparametric Optimization: Online Kernel Learning against Dynamic Comparators," in Intl. Conf. on Continuous Optimization (ICCOPT), Berlin, Germany, Aug. 2019.
[C16] A. S. Bedi, A. Koppel, and K. Rajawat, "Compressed Online Non-parametric Learning," in Learning for Dynamics and Control (L4DC), MIT, Cambridge, MA, USA, May. 2019.
[C15] R. Dixit, A. S. Bedi, and K. Rajawat, " Online Learning over Time-varying Graphs via Proximal Gradient Descent," in Proc. of the IEEE Conf. on Decision and Control (CDC), Nice, France, Dec. 2019.
[C14] A. Koppel, A. S. Bedi, and K. Rajawat, " Controlling the Bias-Variance Tradeoff via Coherent Risk for Robust Learning with Kernels," in IEEE American Control Conference (ACC), Philadelphia, PA, Jul. 10-12, 2019.
[C13] A. Chopra, D. S. Kalhan, A. S. Bedi, Abhishek K. Gupta, and K. Rajawat, " On Socially Optimal Traffic Flow in the Presence of Random Users," in IEEE International Conference on Advanced Networks and Telecommunications Systems (ANTS), Indore, India, Dec. 16-19, 2018.
[C12] H. Pradhan, A. S. Bedi, A. Koppel, and K. Rajawat, "Exact Nonparametric Decentralized Online Optimization," in Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), Anaheim, California, USA, Nov. 2018.
[C11] R. Dixit, A. S. Bedi, R. Tripathi, and K. Rajawat, "Time Varying Optimization via Inexact Proximal Online Gradient Descent," in Proc. 52nd Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2018.
[C10] A. S. Bedi, H. Pradhan, and K. Rajawat, " Decentralized Asynchronous Stochastic Gradient Descent: Convergence Rate Analysis ," in Proc. of the Intl. Conf. on Signal Processing and Communications (SPCOM), Bangalore, India, July 2018.
[C9] A. S. Bedi, A. Koppel, and K. Rajawat, " Asynchronous Saddle Point Method: Interference Management Through Pricing ," in Proc. IEEE Conference on Decision and Control (CDC), Dec. 17-19, 2018.
[C8] A. S. Bedi, P. Sarma, and K. Rajawat, "Adversarial Multi-Agent Target Tracking with Inexact Online Gradient Descent," in Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP), Calgary, Canada, Apr. 15-20, 2018.
[C7] A. S. Bedi, and K. Rajawat, "Wireless Network Optimization via Stochastic Sub-gradient Descent: Rate Analysis," in Proc. of the IEEE Intl. Conf. on Wireless Communications and Networking Conference (WCNC), Barcelona, Spain, Apr. 2018.
[C6] A. S. Bedi, K. Rajawat, and M. Coupechoux, "An Online Approach to D2D Trajectory Utility Maximization Problem," in Proc. of the IEEE Intl. Conf. on Computer Communications (INFOCOM), Honolulu, HI, USA, Apr. 2018.
[C5] A. S. Bedi, A. Koppel, and K. Rajawat, "Beyond Consensus and Synchrony in Decentralized Online Optimization using Saddle Point Method, ," in Proc. of the 51st Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2017. [Asilomar Best Student Paper Finalist].
[C4] A. S. Bedi and K. Rajawat, "Asynchronous Resource Allocation in Distributed Heterogeneous Networks," in Proc. of the IEEE ICC, Paris, France, May 2017.
[C3] A. S. Bedi and K. Rajawat, "Optimal Utilization of Storage Systems under Real-time Pricing,"," in Proc. of the IEEE ICC Workshop on Integrating Communications, Control, and Computing Technologies for Smart Grid, Paris, France, May 2017.
[C2] J. Akhtar, A. S. Bedi, K. Rajawat, and A. K. Jagannatham, "BER-Optimized Robust Precoder design for MIMO-OFDM systems with Insufficient CP," in Proc. of IEEE Globecom, Washington, DC USA, Dec. 2016.
[C1] A. S. Bedi and K. Rajawat, "Online Load Scheduling Under Price and Demand Uncertainty in Smart Grid,," in Proc. of the Intl. Conf. on Signal Processing and Communications (SPCOM), Bangalore, India. June 2016.