Aryan Mokhtari

  • Home
  • Publications
  • News
  • Bio
  • Collaborators
  • Contact
  • CV

Publications 2

Publications

Ph.D. Thesis

  1. A. Mokhtari , “Efficient Methods for Large-Scale Empirical Risk Minimization“, 2017.

Preprints

  1. S. Paternain, A. Mokhtari, and A. Ribeiro, “A Second Order Method for Nonconvex Optimization“, 2017.
  2. A. Mokhtari, M. Eisen, and A. Ribeiro, “IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate“, 2017.
  3. A. Mokhtari, M. Gürbüzbalaban, and A. Ribeiro, “Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate“, 2016.
  4. A. Mokhtari, A. Koppel, and A. Ribeiro, “A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning“, 2016.

Journal Papers

  1. A. Simonetto, A. Koppel, A. Mokhtari, G. Leus, and A. Ribeiro, “Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization“, IEEE Transactions on Automatic Control, vol. 62, no. 11, pp. 5724-5738, Nov. 2017. [ Arxiv version]
  2. T. Chen, A. Mokhtari, X. Wang, A. Ribeiro, and G. B. Giannakis, “Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation“, IEEE Trans. on Signal Process., vol. 65, no. 12, pp. 3078-3098, June 15, 15 2017. [ Arxiv version]
  3. M. Eisen, A. Mokhtari, and A. Ribeiro, “Decentralized Quasi-Newton Methods“, IEEE Transactions on Signal Processing, vol. 65, no. 10, pp. 2613-2628, May 15, 15 2017. [ Arxiv version] [Top 50 downloaded articles in IEEE TSP, March 2017. ]
  4. A. Mokhtari, Q. Ling, and A. Ribeiro, “Network Newton Distributed Optimization Methods“, IEEE Transactions on Signal Processing, vol. 65, no. 1, pp. 146-161, Jan.1, 1 2017. [Arxiv version ] [Top 50 downloaded articles in IEEE TSP, November 2016. ]
  5. A. Mokhtari and A. Ribeiro, “DSA: Decentralized Double Stochastic Averaging Gradient Algorithm“, Journal of Machine Learning Research, 17(61):1-35, 2016.
  6. A. Mokhtari, W. Shi, Q. Ling, and A. Ribeiro, “A Decentralized Second-Order Method with Exact Linear Convergence Rate for Consensus Optimization“, IEEE Transactions on Signal and Information Processing over Networks, vol. 2, no. 4, pp. 507-522, Dec. 2016. [ Arxiv Version ]
  7. A. Mokhtari, W. Shi, Q. Ling, and A. Ribeiro, “DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers“, IEEE Trans. on Signal Process., vol. 64, no. 19, pp. 5158-5173, Oct. 1, 2016. [ Arxiv version ]
  8. A. Simonetto, A. Mokhtari, A. Koppel, G. Leus, and A. Ribeiro, “A Class of Prediction-Correction Methods for Time-Varying Convex Optimization“, IEEE Transactions on Signal Processing, vol. 64, no. 17, pp. 4576-4591, Sept.1, 2016. [ Arxiv version ]
  9. A. Mokhtari and A. Ribeiro, “Global Convergence of Online Limited Memory BFGS“, Journal of Machine Learning Research, vol. 16, pp. 3151-3181, 2015.
  10. A. Mokhtari and A. Ribeiro, “RES: Regularized Stochastic BFGS Algorithm“, IEEE Trans. on Signal Process., vol. 62, no. 23, pp. 6089-6104, December 2014. [ Arxiv version]

Conference Papers

  1. A. Mokhtari, H. Hassani, and A. Karbasi, “Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap“, Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarote, Canary Islands, April 9-11, 2018.
  2. M. Eisen, A. Mokhtari, and A. Ribeiro, “Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method“, Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarote, Canary Islands, April 9-11, 2018.
  3. A. Mokhtari and A. Ribeiro, “First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization,” Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems (NIPS) 2017, December 4-9, 2017, Long Beach, CA, pp. 2057-2065, 2017.
  4. M. Eisen, A. Mokhtari, and A. Ribeiro, “A Doubly Quasi-Newton Method for Decentralized Consensus Optimization,” 2017 51th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 2017.
  5. A. Mokhtari, M. Eisen, and A. Ribeiro, “An Incremental Quasi-Newton Method with a Local Superlinear Convergence Rate,” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, 2017, pp. 4039-4043. [ Arxiv version ]
  6. A. Mokhtari, M. Gürbüzbalaban, and A. Ribeiro, “A Double Incremental Aggregated Gradient Method with Linear Convergence Rate for Large-Scale Optimization,” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, 2017, pp. 4696-4700. [ Arxiv version ]
  7. A. Mokhtari, A. Koppel, G. Scutari, and A. Ribeiro, “Large-Scale NonConvex Stochastic Optimization by Doubly Stochastic Successive Convex Approximation,” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, 2017, pp. 4701-4705. [ Arxiv version ]
  8. A. Mokhtari and A. Ingber, “A Diagonal-Augmented Quasi-Newton Method with Application to Factorization Machines,” 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA, 2017, pp. 2671-2675. [ Arxiv version ]
  9. A. Mokhtari, H. Daneshmand, A. Lucchi, T. Hofmann, and A. Ribeiro, “Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy,” Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems (NIPS) 2016, December 5-10, 2016, Barcelona, Spain, pp. 4062-4070, 2016. [ Supplementary Material ]
  10. T. Chen, A. Mokhtari, X. Wang, A. Ribeiro, and G. B. Giannakis, “A Data-driven Approach to Stochastic Network Optimization“, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington DC, DC, USA, 2016, pp. 510-514.
  11. H. Zhang, W. Shi, A. Mokhtari, A. Ribeiro, and Q. Ling, “Decentralized Constrained Consensus Optimization with Primal-Dual Splitting Projection“, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington DC, DC, USA, 2016, pp. 565-569.
  12. M. Eisen, A. Mokhtari, and A. Ribeiro, “An Asynchronous Quasi-Newton Method for Consensus Optimization“, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington DC, DC, USA, 2016, pp. 570-574.
  13. A. Mokhtari, W. Shi, and Qing Ling, “ESOM: Exact Second-Order Method for Consensus Optimization“, 2016 50th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 2016, pp. 783-787.
  14. A. Koppel, A. Mokhtari, and A. Ribeiro, “Doubly Stochastic Algorithms for Large-Scale Optimization“, 2016 50th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA, 2016, pp. 1705-1709.
  15. A. Mokhtari, S. Shahrampour, A. Jadbabaie, and A. Ribeiro, “Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems“, 2016 IEEE 55th Conference on Decision and Control (CDC), Las Vegas, NV, USA, 2016, pp. 7195-7201. [ Arxiv ]
  16. A. Mokhtari, W. Shi, Q. Ling, and A. Ribeiro,”A Decentralized Second-Order Method for Dynamic Optimization“, 2016 IEEE 55th Conference on Decision and Control (CDC), Las Vegas, NV, USA, 2016, pp. 6036-6043. [ Arxiv]
  17. M. Eisen, A. Mokhtari, and A. Ribeiro, “A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization“, 2016 IEEE 55th Conference on Decision and Control (CDC), Las Vegas, NV, USA, 2016, pp. 1951-1958.[ Arxiv ]
  18. A. Simonetto, A. Koppel, A. Mokhtari, G. Leus, and A. Ribeiro, “A Quasi-Newton Prediction-Correction Method for Decentralized Dynamic Convex Optimization”, 2016 European Control Conference (ECC), Aalborg, Denmark, 2016, pp. 1934-1939. [ Arxiv version ]
  19. A. Mokhtari, A. Koppel, and A. Ribeiro, “Doubly Random Parallel Stochastic Methods for Large Scale Learning“, 2016 American Control Conference (ACC), Boston, MA, USA, 2016, pp. 4847-4852. [ Arxiv version ]
  20. A. Simonetto, A. Mokhtari, A. Koppel, G. Leus, and A. Ribeiro, “A Decentralized Prediction-Correction Method for Networked Time-Varying Convex Optimization“, in Proc. IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing(CAMSAP), pp. 509-512, Cancun, Dec. 13-16, 2015.
  21. A. Mokhtari, W. Shi, Q. Ling, and A. Ribeiro, “Decentralized Quadratically Approximated Alternating Direction Method of Multipliers“, in Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 795-799, Orlando, FL, 2015.
  22. A. Koppel, A. Simonetto, A. Mokhtari, G. Leus, and A. Ribeiro, “Target Tracking with Dynamic Convex Optimization“, in Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 1210-1214, Orlando, FL, 2015.
  23. A. Mokhtari and A. Ribeiro, “Decentralized Double Stochastic Averaging Gradient“, in Proc. Asilomar Conference on signals, systems, and computers, pp. 406-410, Pacific Grove, CA, November 8-11, 2015.
  24. A. Simonetto, A. Koppel, A. Mokhtari, G. Leus, and A. Ribeiro, “Prediction-Correction Methods for Time-Varying Convex Optimization“, in Proc. Asilomar Conference on signals, systems, and computers, pp. 666-670, Pacific Grove, CA, November 8-11, 2015.
  25. A. Mokhtari, Q. Ling, and A. Ribeiro, “An Approximate Newton Method for Distributed Optimization“, in Proc Int. Conf. Acoustics Speech Signal Process. (ICASSP), pp. 2959-2963, Brisbane, Australia, 2015.
  26. A. Mokhtari, Q. Ling, and A. Ribeiro, “Network Newton” , in Proc. Asilomar Conference on signals, systems, and computers, pp. 1621-1625, Pacific Grove, CA, November 2-5, 2014. [ slides ]
  27. A. Mokhtari and A. Ribeiro, “A Quasi-Newton Method for Large Scale Support Vector Machines” , in Proc. Int. Conf. Acoustics Speech Signal Process. (ICASSP), pp. 8302-8306, Florence, Italy, May 4-9 2014.
  28. A. Mokhtari and A. Ribeiro, “Regularized Stochastic BFGS algorithm” , In Proc. IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 1109-1112, Austin, Texas, December 3-5, 2013.
  29. A. Mokhtari and A. Ribeiro, “A Dual Stochastic DFP algorithm for Optimal Resource Allocation in Wireless Systems“, In Proc. IEEE Workshop on Signal Process. Advances in Wireless Commun. (SPAWC), pp. 21-25, Darmstadt, Germany, June 16-19, 2013.

Technical Reports

  1. M. Stern, A. Mokhtari, and A. Ribeiro, “Online Limited-Memory BFGS for Click-Through Rate Prediction“, 2015.
  2. A. Mokhtari and A. Ribeiro, “A Dual Stochastic DFP algorithm for Optimal Resource Allocation in Wireless Systems“, 2013.