Albert S. Berahas

41 papers A 1B 1C 1Journal 33Unranked 5

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A line search framework with restarting for noisy optimization problems. Comput. Optim. Appl. Albert S. Berahas, Michael J. O'Neill, Clément W. Royer
2025	J	`jnl`	A Sequential Quadratic Programming Method With High-Probability Complexity Bounds for Nonlinear Equality-Constrained Stochastic Optimization. SIAM J. Optim. Albert S. Berahas, Miaolan Xie, Baoyu Zhou
2025	J	`jnl`	A flexible gradient tracking algorithmic framework for decentralized optimization. Comput. Optim. Appl. Albert S. Berahas, Raghu Bollapragada, Shagun Gupta
2025	J	`jnl`	Collaborative and Distributed Bayesian Optimization via Consensus. IEEE Trans Autom. Sci. Eng. Xubo Yue, Yang Liu, Albert S. Berahas, Blake N. Johnson, Raed Al Kontar
2025	J	`jnl`	Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients. J. Mach. Learn. Res. Sachin Garg, Albert S. Berahas, Michal Derezinski
2024	J	`jnl`	A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear-Equality-Constrained Optimization with Rank-Deficient Jacobians. Math. Oper. Res. Albert S. Berahas, Frank E. Curtis, Michael O'Neill, Daniel P. Robinson
2024	J	`jnl`	Adaptive Consensus: A Network Pruning Approach for Decentralized Optimization. SIAM J. Optim. Suhail M. Shah, Albert S. Berahas, Raghu Bollapragada
2024	J	`jnl`	Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization. J. Optim. Theory Appl. Albert S. Berahas, Raghu Bollapragada, Shagun Gupta
2024	J	`jnl`	First- and second-order high probability complexity bounds for trust-region methods with noisy oracles. Math. Program. Liyuan Cao, Albert S. Berahas, Katya Scheinberg
2024	J	`jnl`	Gradient Descent in the Absence of Global Lipschitz Continuity of the Gradients. SIAM J. Math. Data Sci. Vivak Patel, Albert S. Berahas
2024	J	`jnl`	Non-Uniform Smoothness for Gradient Descent. Trans. Mach. Learn. Res. Albert S. Berahas, Lindon Roberts, Fred Roosta
2024	J	`jnl`	Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients. CoRR Sachin Garg, Albert S. Berahas, Michal Derezinski
2023	J	`jnl`	Accelerating stochastic sequential quadratic programming for equality constrained optimization using predictive variance reduction. Comput. Optim. Appl. Albert S. Berahas, Jiahao Shi, Zihong Yi, Baoyu Zhou
2023	J	`jnl`	Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design. CoRR Xubo Yue, Raed Al Kontar, Albert S. Berahas, Yang Liu, Zhenghao Zai, Kevin Edgar, Blake N. Johnson
2023	J	`jnl`	Full-low evaluation methods for derivative-free optimization. Optim. Methods Softw. Albert S. Berahas, Oumaima Sohab, Luís Nunes Vicente
2023	J	`jnl`	Non-Uniform Smoothness for Gradient Descent. CoRR Albert S. Berahas, Lindon Roberts, Fred Roosta
2022	J	`jnl`	A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization. Found. Comput. Math. Albert S. Berahas, Liyuan Cao, Krzysztof Choromanski, Katya Scheinberg
2022	J	`jnl`	Limited-memory BFGS with displacement aggregation. Math. Program. Albert S. Berahas, Frank E. Curtis, Baoyu Zhou
2022	J	`jnl`	Quasi-Newton methods for machine learning: forget the past, just sample. Optim. Methods Softw. Albert S. Berahas, Majid Jahani, Peter Richtárik, Martin Takác
2021	J	`jnl`	Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise. SIAM J. Optim. Albert S. Berahas, Liyuan Cao, Katya Scheinberg
2021	J	`jnl`	On the Convergence of Nested Decentralized Gradient Methods With Multiple Consensus and Gradient Steps. IEEE Trans. Signal Process. Albert S. Berahas, Raghu Bollapragada, Ermin Wei
2021	A	`conf`	SONIA: A Symmetric Blockwise Truncated Optimization Algorithm. AISTATS Majid Jahani, MohammadReza Nazari, Rachael Tappenden, Albert S. Berahas, Martin Takác
2021	J	`jnl`	Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization. SIAM J. Optim. Albert S. Berahas, Frank E. Curtis, Daniel P. Robinson, Baoyu Zhou
2020	J	`jnl`	A robust multi-batch L-BFGS method for machine learning. Optim. Methods Softw. Albert S. Berahas, Martin Takác
2020	J	`jnl`	An investigation of Newton-Sketch and subsampled Newton methods. Optim. Methods Softw. Albert S. Berahas, Raghu Bollapragada, Jorge Nocedal
2020	C	`conf`	Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations. ICMLA Zheng Shi, Nur Sila Gulgec, Albert S. Berahas, Shamim N. Pakzad, Martin Takác
2020	J	`jnl`	Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations. CoRR Zheng Shi, Nur Sila Gulgec, Albert S. Berahas, Shamim N. Pakzad, Martin Takác
2020	—	`conf`	Scaling Up Quasi-newton Algorithms: Communication Efficient Distributed SR1. LOD (1) Majid Jahani, MohammadReza Nazari, Sergey Rusakov, Albert S. Berahas, Martin Takác
2020	J	`jnl`	Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization. CoRR Albert S. Berahas, Frank E. Curtis, Daniel P. Robinson, Baoyu Zhou
2019	J	`jnl`	Balancing Communication and Computation in Distributed Optimization. IEEE Trans. Autom. Control. Albert S. Berahas, Raghu Bollapragada, Nitish Shirish Keskar, Ermin Wei
2019	J	`jnl`	Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods. SIAM J. Optim. Albert S. Berahas, Richard H. Byrd, Jorge Nocedal
2019	—	`conf`	Nested Distributed Gradient Methods with Adaptive Quantized Communication. CDC Albert S. Berahas, Charikleia Iakovidou, Ermin Wei
2019	J	`jnl`	Quasi-Newton Methods for Deep Learning: Forget the Past, Just Sample. CoRR Albert S. Berahas, Majid Jahani, Martin Takác
2017	J	`jnl`	A Robust Multi-Batch L-BFGS Method for Machine Learning. CoRR Albert S. Berahas, Martin Takác
2017	J	`jnl`	An Investigation of Newton-Sketch and Subsampled Newton Methods. CoRR Albert S. Berahas, Raghu Bollapragada, Jorge Nocedal
2016	—	`conf`	A Multi-Batch L-BFGS Method for Machine Learning. NIPS Albert S. Berahas, Jorge Nocedal, Martin Takác
2016	J	`jnl`	A Multi-Batch L-BFGS Method for Machine Learning. CoRR Albert S. Berahas, Jorge Nocedal, Martin Takác
2016	B	`conf`	Multi-model robust error correction for face recognition. ICIP Michael Iliadis, Leonidas Spinoulas, Albert S. Berahas, Haohong Wang, Aggelos K. Katsaggelos
2016	—	`conf`	adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs. ECML/PKDD (1) Nitish Shirish Keskar, Albert S. Berahas
2015	J	`jnl`	adaQN: An Adaptive Quasi-Newton Algorithm for Training RNNs. CoRR Nitish Shirish Keskar, Albert S. Berahas
2014	—	`conf`	Sparse representation and least squares-based classification in face recognition. EUSIPCO Michael Iliadis, Leonidas Spinoulas, Albert S. Berahas, Haohong Wang, Aggelos K. Katsaggelos