Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Majid Jahani

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information


Sep 11, 2021
Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtárik, Michael W. Mahoney, Martin Takáč


  Access Paper or Ask Questions

DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction


Jul 03, 2020
Soheil Sadeghi Eshkevari, Martin Takáč, Shamim N. Pakzad, Majid Jahani

* Submitted to Elsevier 

  Access Paper or Ask Questions

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm


Jun 06, 2020
Majid Jahani, Mohammadreza Nazari, Rachael Tappenden, Albert S. Berahas, Martin Takáč

* 38 pages, 74 figures 

  Access Paper or Ask Questions

Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1


May 30, 2019
Majid Jahani, Mohammadreza Nazari, Sergey Rusakov, Albert S. Berahas, Martin Takáč

* 18 pages, 14 figures 

  Access Paper or Ask Questions

Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework


May 30, 2019
Mohammadreza Nazari, Majid Jahani, Lawrence V. Snyder, Martin Takáč


  Access Paper or Ask Questions

Quasi-Newton Methods for Deep Learning: Forget the Past, Just Sample


Jan 28, 2019
Albert S. Berahas, Majid Jahani, Martin Takáč

* 45 pages, 26 figures 

  Access Paper or Ask Questions

Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy


Oct 26, 2018
Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takáč


  Access Paper or Ask Questions

Underestimate Sequences via Quadratic Averaging


Oct 10, 2017
Chenxin Ma, Naga Venkata C. Gudapati, Majid Jahani, Rachael Tappenden, Martin Takáč


  Access Paper or Ask Questions