| Quasi-Newton methods for machine learning: forget the past, just sample AS Berahas, M Jahani, P Richtárik, M Takáč Optimization Methods and Software 37 (5), 1668-1704, 2022 | 72* | 2022 |
| Alternating maximization: Unifying framework for 8 sparse PCA formulations and efficient parallel codes P Richtárik, M Jahani, SD Ahipaşaoğlu, M Takáč Optimization and Engineering, 2020 | 45 | 2020 |
| DynNet: Physics-based neural architecture design for nonlinear structural response modeling and prediction SS Eshkevari, M Takáč, SN Pakzad, M Jahani Engineering Structures 229, 111582, 2021 | 36 | 2021 |
| Efficient distributed hessian free algorithm for large-scale empirical risk minimization via accumulating sample strategy M Jahani, X He, C Ma, A Mokhtari, D Mudigere, A Ribeiro, M Takáč International Conference on Artificial Intelligence and Statistics, 2634-2644, 2020 | 29 | 2020 |
| Scaling up quasi-newton algorithms: Communication efficient distributed sr1 M Jahani, M Nazari, S Rusakov, AS Berahas, M Takáč International Conference on Machine Learning, Optimization, and Data Science …, 2020 | 18 | 2020 |
| Fast and safe: accelerated gradient methods with optimality certificates and underestimate sequences M Jahani, NVC Gudapati, C Ma, R Tappenden, M Takáč Computational Optimization and Applications 79, 369-404, 2021 | 15* | 2021 |
| SONIA: A Symmetric Blockwise Truncated Optimization Algorithm M Jahani, M Nazari, R Tappenden, AS Berahas, M Takáč International Conference on Artificial Intelligence and Statistics, 487-495, 2021 | 12 | 2021 |
| A novel model for bus stop location appropriate for Public Transit Network Design: The case of Central Business Districts (CBD) of Tehran M Jahani, HS MEHDI, M Ghatee, M Jahanshahi International Journal of Smart Electrical Engineering 2 (3), 133-141, 2013 | 8 | 2013 |
| Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information M Jahani, S Rusakov, Z Shi, P Richtárik, MW Mahoney, M Takáč Tenth International Conference on Learning Representations (ICLR 2022), 2022 | 6 | 2022 |
| Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework M Nazari, M Jahani, LV Snyder, M Takáč arXiv preprint arXiv:1905.13562, 2019 | 2 | 2019 |
| Deep learning model training system M Jahani, JD Griffin, S Yektamaram, Z Wenwen US Patent 10,949,747, 2021 | | 2021 |
| Efficient and Scalable Optimization Methods for Training Large-Scale Machine Learning Models M Jahani Lehigh University, 2021 | | 2021 |
| Sampled Quasi-Newton Methods for Deep Learning AS Berahas, M Jahani, M Takác 11th OPT Workshop on Optimization for Machine Learning, 2019 | | 2019 |
| Grow Your Samples and Optimize Better via Distributed Newton CG and Accumulating Strategy. M Jahani, X He, C Ma, A Mokhtari, D Mudigere, A Ribeiro, M Takáč NeurIPS 2019, Beyond First Order Methods in Machine Learning Systems Workshop, 2019 | | 2019 |
| Distributed Restarting NewtonCG Method for Large-Scale Empirical Risk Minimization M Jahani, X He, C Ma, D Mudigere, A Mokhtari, A Ribeiro, M Takac | | 2017 |
| DOUBLY ADAPTIVE SCALED ALGORITHM FOR MACHINE LEARNING USING 2 nd ORDER INFORMATION M Jahani, S Rusakov, Z Shi, P Richtárik, MW Mahoney, M Takác | | |
| A minibatch stochastic Quasi-Newton method adapted for nonconvex deep learning problems JD Griffina, M Jahanib, M Takáčc, S Yektamarama, W Zhoua | | |
Martin TakáčMohamed bin Zayed University of Artificial Intelligence (MBZUAI)Verified email at mbzuai.ac.ae
