Albert S. Berahas

According to our database, Albert S. Berahas authored at least 26 papers between 2014 and 2024.

Collaborative distances:

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

2024

First- and second-order high probability complexity bounds for trust-region methods with noisy oracles.

Liyuan Cao, Albert S. Berahas, Katya Scheinberg

Math. Program., September, 2024

Non-Uniform Smoothness for Gradient Descent.

Albert S. Berahas, Lindon Roberts, Fred Roosta

Trans. Mach. Learn. Res., 2024

Adaptive Consensus: A Network Pruning Approach for Decentralized Optimization.

Suhail M. Shah, Albert S. Berahas, Raghu Bollapragada

SIAM J. Optim., 2024

Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients.

Sachin Garg, Albert S. Berahas, Michal Derezinski

CoRR, 2024

2023

Accelerating stochastic sequential quadratic programming for equality constrained optimization using predictive variance reduction.

Albert S. Berahas, Jiahao Shi, Zihong Yi, Baoyu Zhou

Comput. Optim. Appl., September, 2023

Full-low evaluation methods for derivative-free optimization.

Albert S. Berahas, Oumaima Sohab, Luís Nunes Vicente

Optim. Methods Softw., March, 2023

Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design.

Xubo Yue, Raed Al Kontar, Albert S. Berahas, Yang Liu, Zhenghao Zai, Kevin Edgar, Blake N. Johnson

CoRR, 2023

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

Limited-memory BFGS with displacement aggregation.

Albert S. Berahas, Frank E. Curtis, Baoyu Zhou

Math. Program., 2022

A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization.

Albert S. Berahas, Liyuan Cao, Krzysztof Choromanski, Katya Scheinberg

Found. Comput. Math., 2022

2021

On the Convergence of Nested Decentralized Gradient Methods With Multiple Consensus and Gradient Steps.

Albert S. Berahas, Raghu Bollapragada, Ermin Wei

IEEE Trans. Signal Process., 2021

Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise.

Albert S. Berahas, Liyuan Cao, Katya Scheinberg

SIAM J. Optim., 2021

Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization.

Albert S. Berahas, Frank E. Curtis, Daniel P. Robinson, Baoyu Zhou

SIAM J. Optim., 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

A robust multi-batch L-BFGS method for machine learning.

Albert S. Berahas, Martin Takác

Optim. Methods Softw., 2020

An investigation of Newton-Sketch and subsampled Newton methods.

Albert S. Berahas, Raghu Bollapragada, Jorge Nocedal

Optim. Methods Softw., 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

Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations.

Zheng Shi, Nur Sila Gulgec, Albert S. Berahas, Shamim N. Pakzad, Martin Takác

Proceedings of the 19th IEEE International Conference on Machine Learning and Applications, 2020

2019

Balancing Communication and Computation in Distributed Optimization.

Albert S. Berahas, Raghu Bollapragada, Nitish Shirish Keskar, Ermin Wei

IEEE Trans. Autom. Control., 2019

Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods.

Albert S. Berahas, Richard H. Byrd, Jorge Nocedal

SIAM J. Optim., 2019

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

Albert S. Berahas, Majid Jahani, Martin Takác

CoRR, 2019

Nested Distributed Gradient Methods with Adaptive Quantized Communication.

Albert S. Berahas, Charikleia Iakovidou, Ermin Wei

Proceedings of the 58th IEEE Conference on Decision and Control, 2019

2016

adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs.

Nitish Shirish Keskar, Albert S. Berahas

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2016

A Multi-Batch L-BFGS Method for Machine Learning.

Albert S. Berahas, Jorge Nocedal, Martin Takác

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Multi-model robust error correction for face recognition.

Michael Iliadis, Leonidas Spinoulas, Albert S. Berahas, Haohong Wang, Aggelos K. Katsaggelos

Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

2014

Sparse representation and least squares-based classification in face recognition.

Michael Iliadis, Leonidas Spinoulas, Albert S. Berahas, Haohong Wang, Aggelos K. Katsaggelos

Proceedings of the 22nd European Signal Processing Conference, 2014