Skip to main content

Publications


    Submissions Under Review

  1. A. Mokhtari and A. Koppel, "High-Dimensional Nonconvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation " in IEEE Transactions on Signal Processing (under review), Nov. 2019.


  2. H. Kumar, A. Koppel, and A. Ribeiro. "On the Sample Complexity of Actor-Critic Method for Reinforcement Learning with Function Approximation" in Machine Learning (under review), Springer, Oct. 2019.


  3. A.S. Bedi, K. Rajawat, V. Aggarwal, and A. Koppel. "Escaping Saddle Points in Successive Convex Approximation" in IEEE Trans. Signal Processing (under review), Oct. 2019.


  4. D. S. Kalhan, A. S. Bedi, A. Koppel, K. Rajawat, H. Hassani, A. Gupta, and A. Banerjee. `` Dynamic Online Learning via Frank-Wolfe Algorithm ,” in IEEE Trans. Signal Process , (under review), Sept. 2019


  5. A. Koppel, A. S. Bedi, V. Elvira, and B.M. Sadler. ``Approximate Shannon Sampling in Importance Sampling: Nearly Consistent Finite Particle Estimates,” in Statistics and Computing, Springer (under review), Sept. 2019


  6. A. S. Bedi, A. Koppel, K. Rajawat, and B.M. Sadler. ``Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony,” in IEEE Trans. Signal Processing (under review), Sept. 2019


  7. R. Pradhan, Amrit S. Bedi, A. Koppel, and K. Rajawat. " Adaptive Kernel Learning in Heterogeneous Networks " in IEEE Trans. Signal Processing (under review), Aug. 2019.


  8. Amrit S. Bedi, A. Koppel, and K. Rajawat. " Nonparametric Compositional Stochastic Optimization " in IEEE Trans. Signal Processing (under review), Feb. 2019.


  9. K. Zhang, A. Koppel, H. Zhu, and T. M. Baser. "Global Convergence of Policy Gradient Methods: A Nonconvex Optimization Perspective" in SIAM Journal on Control and Optimization (under review), Jan. 2019.


  10. A. Koppel, E. Tolstaya, E. Stump, and A. Ribeiro. "Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems" in SIAM Journal on Optimization (under review), Sept. 2019. [Code]


  11. A. Koppel, G. Warnell, E. Stump, P. Stone, and A. Ribeiro. ``Policy Evaluation in Continuous MDPs with Efficient Kernelized Gradient Temporal Difference," in IEEE Trans. Automatic Control (under review), Dec. 2017. [ArXiV verson]

  12. M. Fazlyab, A. Koppel, V. Preciado, and A. Ribeiro, ``A Variational Approach to Dual Methods for Constrained Convex Optimization," in IEEE Trans. Automatic Control (Under review), Nov. 2017.


  13. A. Mokhtari, A. Koppel, and A. Ribeiro, "A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning," in Journal of Machine Learning Research (under review), June 2016.


  14. 2019

  15. A. Koppel, K. Zhang, H. Zhu, and T. M. Baser. "Projected Stochastic Primal-Dual Method for Constrained Online Learning with Kernels" in IEEE Trans. Signal Processing, Vol: 67 , Issue: 10 , May 2019


  16. A. S. Bedi, A. Koppel, and K. Rajawat. "Asynchronous Online Learning in Multi-Agent Systems with Proximity Constraints" in IEEE Trans. Signal Info. Process. Over Networks, Mar. 2019.


  17. A. Koppel, G. Warnell, E. Stump, and A. Ribeiro, "Parsimonious Online Learning with Kernels via Sparse Projections in Function Space," in the Journal of Machine Learning Research, Jan. 2019. [Video]


  18. A. S. Bedi, A. Koppel, and K. Rajawat, "Asynchronous Saddle Point Algorithm for Stochastic Optimization in Heterogeneous Networks" in IEEE Trans. Signal Process. (to appear), Jan. 2019.


  19. 2018

  20. A. Koppel, S. Paternain, C. Richard, and A. Ribeiro, "Decentralized Online Learning with Kernels", in IEEE Trans. Signal Process, Apr. 2018.


  21. 2017

  22. A. Simonetto, A. Koppel, A. Mokhtari, G. Leus, and A. Ribeiro, "Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization," in IEEE Trans. Automatic Control, Apr. 2017.


  23. A. Koppel, B. Sadler, and A. Ribeiro, "Proximity without Consensus in Online Multi-Agent Optimization," in IEEE Trans. Signal Process., Mar. 2017.


  24. A. Koppel, G. Warnell, E. Stump, and A. Ribeiro, "D4L: Decentralized Dynamic Discrminative Dictionary Learning," in IEEE Trans. Signal and Info. Process over Networks, Feb. 2017. [Video]


  25. 2016

  26. A. Simonetto,  A. Mokhtari, A. Koppel, G. Leus, and A. Ribeiro, "A Class of Prediction-Correction Methods for Time-Varying Convex Optimization," in IEEE Trans. Signal Process., May. 2016.


  27. 2015

  28. A. Koppel, F. Jakubeic, and A. Ribeiro, “A saddle point algorithm for networked online convex optimization,” in IEEE Trans. Signal Process., Oct 2015. [Video]


    2020

  1. D. S. Kalhan, A. S. Bedi, A. Koppel, K. Rajawat, A. Gupta, and A. Banerjee, “ Projection Free Dynamic Online Learning,” in IEEE Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP) (submitted), Barcelona, Spain, May. 4-8, 2020.


  2. H. Pradhan, A. S. Bedi, A. Koppel, and K. Rajawat, “ Improved Rates for Multi-Agent Online Kernel Learning in Heterogeneous Networks,” in IEEE Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP) (submitted), Barcelona, Spain, May. 4-8, 2020.


  3. Z. Gao, A. Koppel, and A. Ribeiro, “ Balancing Rates and Variance via Adaptive Batch-Sizes in First-Order Stochastic Optimization,” in IEEE Proc. Int. Conf. Acoustics Speech Signal Process (ICASSP) (submitted), Barcelona, Spain, May. 4-8, 2020.


  4. A.S. Bedi, A. Koppel, K. Rajawat, B.M. Sadler, “ Trading Dynamic Regret for Model Complexity in Nonstationary Nonparametric Optimization,” in IEEE American Control Conference (submitted), Denver, Colorado, Jul. 1-1, 2020.


  5. 2019

  6. H. Kumar, A. Koppel, and A. Ribeiro, “On the Sample Complexity of Actor-Critic for Reinforcement Learning,” in NeurIPS Optimization Foundations of Reinforcement Learning Workshop (to appear), Vancouver, CA, Dec. 14, 2019.


  7. K. Zhang, A. Koppel, H. Zhu, T. Basar, “Convergence and Iteration Complexity of Policy Gradient Methods for Infinite-horizon Reinforcement Learning,” in IEEE Conference on Decision and Control (to appear), Nice, France, Dec. 11-13, 2019.


  8. S. Bhatt, A. Koppel, V Krishnamurthy, “Policy Gradient using Weak Derivatives for Reinforcement Learning,” in IEEE Conference on Decision and Control (to appear), Nice, France, Dec. 11-13, 2019.


  9. S. Bhatt, A. Koppel, V. Krishnamurthy, "Policy Search using Jordan Decomposition for Reinforcement Learning,"in IEEE Conference on Information Sciences and Systems (CISS), Baltimore, MD, Mar. 20-22, 2019.


  10. K. Zhang, A. Koppel, H. Zhu, T. Basar, "Policy Search in Infinite-Horizon Discounted Reinforcement Learning: Advances through Connections to Non-Convex Optimization," in IEEE Conference on Information Sciences and Systems (CISS), Baltimore, MD, Mar. 20-22, 2019.


  11. A. Koppel, A. S. Bedi, K. Rajawat, Controlling the Bias-Variance Tradeoff via Coherent Risk for Robust Learning with Kernels,” in IEEE American Control Conference (to appear), Philadelphia, PA, July 10-12, 2019.

  12. A. Koppel , "Consistent Online Gaussian Process Regression Without the Sample Complexity Bottleneck,"in IEEE American Control Conference (ACC), Philadelphia, PA, Jul. 10-12, 2019.


  13. 2018

  14. A. S. Bedi, A. Koppel, and K. Rajawat, "Asynchronous Saddle Point Method: Interference Management Through Pricing," in IEEE Conf. on Decision and Control (CDC), Miami Beach, FL, Dec. 17-19, 2018.


  15. K. Zhang, H. Zhu, T. Baser, and A. Koppel , "Projected Stochastic Primal-Dual Method for Constrained Online Learning with Kernels,"in IEEE Conf. on Decision and Control (CDC), Miami Beach, FL, Dec. 17-19, 2018.


  16. H. Pradhan, A. S. Bedi, A. Koppel, and K. Rajawat, "Exact Decentralized Online Nonparametric Optimization," in IEEE Global Conf. on Signals and Info. Processing, Anaheim, CA, Nov. 26-28, 2018.


  17. A. Koppel, S. Paternain, C. Richard, and A. Ribeiro, "Decentralized Online Nonparametric Learning," in IEEE Asilomar Conf. on Signals, Systems, Computers, Pacific Grove, CA, Oct. 28-31, 2018.


  18. E. Tolstaya, E. Stump, A. Koppel, and A. Ribeiro, "Composable Learning with Sparse Kernel Representations," in International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, Oct. 1-5, 2018.


  19. E. Tolstaya, A. Koppel, E. Stump, and A. Ribeiro, "Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems," in American Control Conference , Milwaukee, WI, June 27-29, 2018. [Slides][Code]


  20. A. Koppel,  A. Mokhtari, and A. Ribeiro, "Parallel Stochastic Successive Convex Approximation Method for Large-Scale Dictionary Learning," in Proc. Int. Conf. Acoustics Speech Signal Process , Calgary, Canada, Apr. 15-20, 2018. [Poster]


  21. 2017

  22. A. Koppel, S. Paternain, C. Richard, and A. Ribeiro, "Decentralized Efficient Nonparametric Stochastic Optimization", in IEEE Global Conference on Signal and Information Processing, Montreal, Canada, Nov. 14-16, 2017. [Slides]


  23. A. S. Bedi, A. Koppel, and K. Rejawat, "Beyond Consensus and Synchrony in Decentralized Online Optimization using Saddle Point Method" in Proc. Asilomar Conf. on Signals Systems Computers, Best Paper Finalist, Pacific Grove, CA, Oct. 29-Nov. 1, 2017. [Slides]


  24. M. Fazlyab, A. Koppel, V. Preciado, and A. Ribeiro, ``A Variational Approach to Dual Methods for Constrained Convex Optimization," in American Control Conference, Seattle, WA, May 24-26, 2017.


  25. A. Mokhtari, A. Koppel,  and G. Scutari, A. Ribeiro, "Large-Scale Non-Convex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation," in Proc. Int. Conf. Acoustics Speech Signal Process, New Orleans, LA, USA Mar. 5-9 2017. [Poster]


  26. A. Koppel, G. Warnell, E. Stump, and A. Ribeiro, "Parsimonious Online Learning with Kernels via Sparse Projections in Function Space," in Proc. Int. Conf. Acoustics Speech Signal Process, New Orleans, LA, USA Mar. 5-9 2017. [Poster]


  27. 2016

  28. A. Koppel, B. M. Sadler, and A. Ribeiro, "Decentralized Online Optimization with Heterogeneous Data Sources", in IEEE Global Conference on Signal and Information Processing, Dec. 7-9 2016.  [Slides]


  29. A. Koppel, A. Mokhtari, and A. Ribeiro, "Doubly Random Parallel Stochastic Methods for Large Scale Learning," in Proc. Asilomar Conf. on Signals Systems Computers, Pacific Grove, CA, November 7-9 2016. [Slides]


  30. A. Koppel, J. Fink, G. Warnell, E. Stump, and A. Ribeiro, "Online Learning for Characterizing Unknown Environments in Ground Robotic Vehicle Models," in Proc. Int. Conf. Intelligent Robotics and Systems, Daejeon, Korea, Oct 9-14 2016. [Slides]


  31. A. Simonetto, A. Koppel, A. Mokhtari, G. Leus, and A. Ribeiro, “A Quasi-Newton Prediction-Correction Method for Decentralized Dynamic Convex Optimization”, in European Control Conference, Aalborg, Denmark, June 29 - July 1, 2016.


  32. A. Mokhtari, A. Koppel, and A. Ribeiro, "Doubly Random Parallel Stochastic Methods for Large Scale Learning," in American Control Conference, Boston, MA, July 6-8 2016. [Slides]


  33. A. Koppel, B. M. Sadler and A. Ribeiro, "Proximity without consensus in online multi-agent optimization," in Proc. Int. Conf. Acoustics Speech Signal Process, Shanghai, China, Mar. 20-25 2016. [Poster]


  34. 2015

  35. A. Simonetto, A. Mokhtari, A. Koppel, G. Leus, and A. Ribeiro, "A Decentralized Prediction-Correction Method for Networked Time-Varying Convex Optimization", IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, Dec. 13-16 2015.


  36. A. Koppel, A. Simonetto, A. Mokhtari, G. Leus, and A. Ribeiro, "Target Tracking with Dynamic Convex Optimization", in IEEE Global Conference on Signal and Information Processing, Dec. 14-16 2015. [Slides]

  37. A. Simonetto, A. Koppel, A. Mokhtari, G. Leeus, and A. Ribeiro "Prediction-Correction Methods for Time-Varying Convex Optimization." inProc. Asilomar Conf. on Signals Systems Computers, Pacific Grove, CA, November 8-11 2015. [Slides]


  38. A. Koppel, G. Warnell, and E. Stump, "Task-Driven Dictionary Learning in Distributed Online Settings."in Proc. Asilomar Conf. on Signals Systems Computers, Pacific Grove, CA, November 8-11 2015. [Slides]


  39. A. Koppel, G. Warnell, E. Stump, and A. Ribeiro,"D4L: Decentralized Dynamic Discriminative Dictionary Learning," in Proc. Int. Conf. Intelligent Robotics and Systems, Hamburg, Germany, Sep 28-Oct2 2 015. [Slides]


  40. A. Koppel, F. Jakubeic and A. Ribeiro, "Regret Bounds of a distributed saddle point algorithm," in Proc. Int. Conf. Acoustics Speech Signal Process., Brisbane Australia, Apr 19-24 2015. [Slides]


  41. 2014

  42. A. Koppel, F. Y. Jakubiec, and A. Ribeiro, "A Saddle Point Algorithm for Networked Online Convex Optimization.” in 39th Proc. Int. Conf. Acoust. Speech Signal Process., May 4-9 2014, pp. 8292–8296. [Post]


  1. A. Koppel. "Stochastic Optimization for Multi-Agent Statistical Learning and Control," PhD Dissertation, Dept. of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, July 2017.


  2. A. Koppel. “Parameter Estimation in High-Dimensions using Doubly Stochastic Approximation," Master's Thesis, Statistics Department, The Wharton School, University of Pennsylvania, Philadelphia, PA, May 2017.


  3. V. Ganesan, A. Koppel, S. Han, J. Conroy, A. Wickenden, R. Murray, and W. Nothwang. “Implementation and Validation of Bioplausible Visual Servoing Control.” ARL-TR- 6387; U.S. Army Research Laboratory: Adelphi, MD, March 2013.


  4. A. Koppel, E. Stump, W. Nothwang, and B. Sadler. “An Adaptive Stochastic Differential System for Multi-Agent Coordination.” Army Research Laboratory Technical Report. Aug. 2012. (Preprint).

  5. A. Koppel*, V. Ganesan,* A. Wickenden, W. Nothwang. “Slow Computing Simulation of Bio-Plausible Control.” ARL-TR-5959; U.S. Army Research Laboratory: Adelphi, MD, March 2012


  6. A. Koppel and R. Feres. “Stochastic Methods for the Lotka-Volterra Model with Migration.” Bachelors Honors Thesis. Washington University in St. Louis, Mar. 2011.


    2020

  1. Industrial and Operations Engineering Department Colloquium, University of Michigan, Ann Arbor, MI, Jan 17, 2020

  2. 2019

  3. IEEE Conference on Decision and Control, Nice, France, Dec 11-13, 2019

  4. Workshop on New Directions in Reinforcement Learning and Control, Institute for Advanced Study, Princeton, NJ, Nov. 8, 2019 [Video]

  5. IEEE Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 4-6, 2019

  6. INFORMS Annual Meeting, Seattle, WA, Oct. 20-23, 2019

  7. SIAM International Conference on Continuous Optimization (ICCOPT), Technical University (TU) of Berlin, Berlin, Germany, Aug. 5-8, 2019

  8. Learning for Dynamics and Control (L4DC) Poster, Massachusetts Institute of Technology, Cambridge, MA, May 30, 2019

  9. Artificial Intelligence and Machine Learning Seminar, Lehigh University, Bethlehem, PA, May 9, 2019

  10. Industrial and Systems Engineering Seminar, Lehigh University, Bethlehem, PA, May 8, 2019

  11. Intelligent Systems Seminar, Applied Physics Laboratory, Johns Hopkins University, Laurel, MD, May 2, 2019

  12. Visiting Colloquium, Johns Hopkins University, Baltimore, MD, Mar. 12, 2019

  13. Electrical and Computer Engineering Colloquium, Princeton University, Princeton, NJ, Feb. 27, 2019

  14. Visiting Colloquium, Cornell Tech, New York, NY, Feb. 26, 2019

  15. Machine Learning Colloquium, Samsung AI Center, New York, NY, Feb. 25, 2019

  16. Visiting Colloquium, University of Pennsylvania, Philadelphia, PA, Jan. 31, 2019

  17. Workshop on Machine Learning for Networked Data, New York University, New York, NY, Jan. 29, 2019

  18. Electrical and Computer Engineering Colloquium, George Mason University, Fairfax, VA, Jan. 23, 2019

  19. 2018

  20. Computer Science Colloquium, Washington University, St. Louis, MO, Nov. 16, 2018

  21. Intelligent Systems Seminar, U.S. Army Research Laboratory, Adelphi, MD, Nov. 13, 2018

  22. Machine Learning Seminar, Facebook Artificial Intelligence Research (FAIR), Menlo Park, CA, Nov. 1, 2018

  23. DIMACS/MOPTA/TRIPODS Workshop on Machine Learning and Optimization, Lehigh University, Bethlehem, PA, Aug 13-15, 2018

  24. International Symposium on Mathematical Programming (ISMP), Place de la Victoire, University of Bordeaux, Bordeaux, France, July 2-5, 2018

  25. Learning Theory Seminar, Cornell Tech., New York, NY, May 8, 2018

  26. INFORMS Optimization Society Conference, Denver, CO, Mar. 23, 2018

  27. Artificial Intelligence Seminar, Carnegie Melon University, Pittsburgh, PA, Feb. 20, 2018

  28. Machine Learning Seminar, Army Research Laboratory, Adelphi, MD, Feb. 15, 2018

  29. Laboratory on Information and Decision Systems (LIDS) Seminar, Massachusetts Institute of Technology, Cambridge, MA, Jan. 30, 2018

  30. Machine Learning Seminar, George Washington University, Washington, DC, Jan. 23, 2018

  31. 2017

  32. Intelligent Systems Seminar, Army Research Laboratory, Adelphi, MD, Dec. 10, 2017

  33. INFORMS Annual Meeting, Houston, TX, Oct. 24, 2017

  34. Science Cafe, Army Research Laboratory, Adelphi, MD, Oct. 10, 2017

  35. DIMACS Workshop on Distributed Optimization, Information Processing, and Learning, Rutgers University, New Brunswick, NJ, Aug. 23, 2017

  36. Learning Theory Seminar, Microsoft Research, Redmond, WA, May 23, 2017

  37. 2016

  38. Applied Probability Seminar, IBM Watson Research Center, Yorktown Heights, NY, Oct. 5, 2016

  39. Phd Student Colloquium, University of Pennsylvania, Philadelphia, PA, Sep. 21, 2016

  40. Optimization and Learning Seminar, University of Science & Technology of China (USTC) Hefei, China, Mar. 29, 2016

  41. INFORMS Optimization Society Conference, Princeton University, Princeton, NJ, Mar. 19, 2016

  42. 2015

  43. Communications and Networking Seminar, University of Southern California, Aug. 19, 2015.

  44. Signal and Information Processing Seminar, University of California, Los Angeles (UCLA), AUG. 18, 2015.