Majid Jahani

According to our database, Majid Jahani authored at least 10 papers between 2017 and 2022.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2022

Quasi-Newton methods for machine learning: forget the past, just sample.

Albert S. Berahas, Majid Jahani, Peter Richtárik, Martin Takác

Optim. Methods Softw., 2022

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

Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtárik, Michael W. Mahoney, Martin Takác

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Fast and safe: accelerated gradient methods with optimality certificates and underestimate sequences.

Majid Jahani, Naga Venkata C. Gudapati, Chenxin Ma, Rachael Tappenden, Martin Takác

Comput. Optim. Appl., 2021

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm.

Majid Jahani, MohammadReza Nazari, Rachael Tappenden, Albert S. Berahas, Martin Takác

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

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

Soheil Sadeghi Eshkevari, Martin Takác, Shamim N. Pakzad, Majid Jahani

CoRR, 2020

Scaling Up Quasi-newton Algorithms: Communication Efficient Distributed SR1.

Majid Jahani, MohammadReza Nazari, Sergey Rusakov, Albert S. Berahas, Martin Takác

Proceedings of the Machine Learning, Optimization, and Data Science, 2020

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

Majid Jahani, Xi He, Chenxin Ma, Aryan Mokhtari, Dheevatsa Mudigere, Alejandro Ribeiro, Martin Takác

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

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

MohammadReza Nazari, Majid Jahani, Lawrence V. Snyder, Martin Takác

CoRR, 2019

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

Albert S. Berahas, Majid Jahani, Martin Takác

CoRR, 2019

2017

Underestimate Sequences via Quadratic Averaging.

Chenxin Ma, Naga Venkata C. Gudapati, Majid Jahani, Rachael Tappenden, Martin Takác

CoRR, 2017