Albert S. Berahas
Albert S. Berahas
Assistant Professor, University of Michigan
Verified email at umich.edu - Homepage
Title
Cited by
Cited by
Year
A multi-batch L-BFGS method for machine learning
AS Berahas, J Nocedal, M Takác
Advances in Neural Information Processing Systems, 1055-1063, 2016
622016
An Investigation of Newton-Sketch and Subsampled Newton Methods
AS Berahas, R Bollapragada, J Nocedal
Optimization Methods and Software 35 (4), 661-680, 2020
562020
Balancing communication and computation in distributed optimization
AS Berahas, R Bollapragada, NS Keskar, E Wei
IEEE Transactions on Automatic Control 64 (8), 3141-3155, 2018
362018
adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs
NS Keskar, AS Berahas
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2016
282016
Quasi-newton methods for deep learning: Forget the past, just sample
AS Berahas, M Jahani, M Takáč
arXiv preprint arXiv:1901.09997, 2019
182019
Derivative-free optimization of noisy functions via quasi-Newton methods
AS Berahas, RH Byrd, J Nocedal
SIAM Journal on Optimization 29 (2), 965-993, 2019
172019
A theoretical and empirical comparison of gradient approximations in derivative-free optimization
AS Berahas, L Cao, K Choromanski, K Scheinberg
arXiv preprint arXiv:1905.01332, 2019
142019
A robust multi-batch l-bfgs method for machine learning
AS Berahas, M Takáč
Optimization Methods and Software 35 (1), 191-219, 2020
132020
Sparse representation and least squares-based classification in face recognition
M Iliadis, L Spinoulas, AS Berahas, H Wang, AK Katsaggelos
2014 22nd European Signal Processing Conference (EUSIPCO), 526-530, 2014
92014
Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1
M Jahani, M Nazari, S Rusakov, AS Berahas, M Takáč
arXiv preprint arXiv:1905.13096, 2019
42019
Global convergence rate analysis of a generic line search algorithm with noise
AS Berahas, L Cao, K Scheinberg
arXiv preprint arXiv:1910.04055, 2019
32019
Nested Distributed Gradient Methods with Adaptive Quantized Communication
AS Berahas, C Iakovidou, E Wei
58th IEEE Conference on Decision and Control (CDC), 1519-1525, 2019
32019
Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization
AS Berahas, L Cao, K Choromanski, K Scheinberg
arXiv preprint arXiv:1905.13043, 2019
22019
Multi-model robust error correction for face recognition
M Iliadis, L Spinoulas, AS Berahas, H Wang, AK Katsaggelos
2016 IEEE International Conference on Image Processing (ICIP), 3229-3233, 2016
22016
Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization
A Berahas, FE Curtis, DP Robinson, B Zhou
arXiv preprint arXiv:2007.10525, 2020
2020
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm
M Jahani, M Nazari, R Tappenden, AS Berahas, M Takáč
arXiv preprint arXiv:2006.03949, 2020
2020
Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
Z Shi, NS Gulgec, AS Berahas, SN Pakzad, M Takáč
arXiv preprint arXiv:2006.01892, 2020
2020
On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps
AS Berahas, R Bollapragada, E Wei
arXiv preprint arXiv:2006.01665, 2020
2020
An Investigation of Newton-Sketch and Subsampled Newton Methods: Supplementary Materials
AS Berahas, R Bollapragada, J Nocedal
2020
Limited-Memory BFGS with Displacement Aggregation
AS Berahas, FE Curtis, B Zhou
arXiv preprint arXiv:1903.03471, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20