pith. sign in

Aryan Mokhtari

Identifiers

  • name variant Aryan Mokhtari 0.60 · backfill

Papers (35)

  1. Curriculum Learning-Guided Progressive Distillation in Large Language Models cs.LG · 2026 · author #4
  2. DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate math.OC · 2019 · author #3
  3. Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free cs.LG · 2019 · author #3
  4. Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE math.OC · 2018 · author #3
  5. Escaping Saddle Points in Constrained Optimization cs.LG · 2018 · author #1
  6. Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication stat.ML · 2018 · author #2
  7. Direct Runge-Kutta Discretization Achieves Acceleration math.OC · 2018 · author #2
  8. Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization math.OC · 2018 · author #1
  9. Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings math.OC · 2018 · author #1
  10. Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap math.OC · 2017 · author #1
  11. First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization cs.LG · 2017 · author #1
  12. A Newton-Based Method for Nonconvex Optimization with Fast Evasion of Saddle Points math.OC · 2017 · author #2
  13. Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method math.OC · 2017 · author #2
  14. IQN: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate math.OC · 2017 · author #1
  15. Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate math.OC · 2016 · author #1
  16. Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation math.OC · 2016 · author #2
  17. A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning cs.LG · 2016 · author #1
  18. Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy cs.LG · 2016 · author #1
  19. Decentralized Quasi-Newton Methods math.OC · 2016 · author #2
  20. A Decentralized Second-Order Method for Dynamic Optimization math.OC · 2016 · author #1
  21. A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization math.OC · 2016 · author #2
  22. Doubly Random Parallel Stochastic Methods for Large Scale Learning cs.LG · 2016 · author #1
  23. Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems cs.LG · 2016 · author #1
  24. Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization math.OC · 2016 · author #3
  25. A Decentralized Second-Order Method with Exact Linear Convergence Rate for Consensus Optimization math.OC · 2016 · author #1
  26. Decentralized Quadratically Approximated Alternating Direction Method of Multipliers math.OC · 2015 · author #1
  27. A Class of Prediction-Correction Methods for Time-Varying Convex Optimization cs.IT · 2015 · author #2
  28. DQM: Decentralized Quadratically Approximated Alternating Direction Method of Multipliers math.OC · 2015 · author #1
  29. DSA: Decentralized Double Stochastic Averaging Gradient Algorithm math.OC · 2015 · author #1
  30. Network Newton-Part II: Convergence Rate and Implementation math.OC · 2015 · author #1
  31. Network Newton-Part I: Algorithm and Convergence math.OC · 2015 · author #1
  32. Network Newton math.OC · 2014 · author #1
  33. Global Convergence of Online Limited Memory BFGS math.OC · 2014 · author #1
  34. A Quasi-Newton Method for Large Scale Support Vector Machines cs.LG · 2014 · author #1
  35. RES: Regularized Stochastic BFGS Algorithm cs.LG · 2014 · author #1

Mentions

  • 1402.4861 #1 · backfill · confidence 0.70 Aryan Mokhtari
  • 1401.7625 #1 · backfill · confidence 0.70 Aryan Mokhtari

Frequent Coauthors