25 citations · 77 across the 32 of their papers we have counts for
37 papers
A Gradient Sampling Algorithm for Noisy Nonsmooth Nonconvex Optimization
Albert S. Berahas, Frank E. Curtis, Lara Zebiane
An algorithm is proposed, analyzed, and tested for minimizing locally Lipschitz objective functions that may be nonconvex and/or nonsmooth. The algorithm, which is built upon the g…
Negative Curvature Methods with High-Probability Complexity Guarantees for Stochastic Nonconvex Optimization
Albert S. Berahas, Raghu Bollapragada, Wanping Dong
This paper develops negative curvature methods for continuous nonlinear unconstrained optimization in stochastic settings, in which function, gradient, and Hessian information is a…
A line search framework with restarting for noisy optimization problems
Albert S. Berahas, Michael J. O'Neill, Clément W. Royer
Nonlinear optimization methods are typically iterative and make use of gradient information to determine a direction of improvement and function information to effectively check fo…
Retrospective Approximation Sequential Quadratic Programming for Stochastic Optimization with General Deterministic Nonlinear Constraints
Albert S. Berahas, Raghu Bollapragada, Shagun Gupta
In this paper, we propose a framework based on the Retrospective Approximation (RA) paradigm to solve optimization problems with a stochastic objective function and general nonline…
Optimistic Noise-Aware Sequential Quadratic Programming for Equality Constrained Optimization with Rank-Deficient Jacobians
Albert S. Berahas, Jiahao Shi, Baoyu Zhou
We propose and analyze a sequential quadratic programming algorithm for minimizing a noisy nonlinear smooth function subject to noisy nonlinear smooth equality constraints. The alg…
Exploiting Negative Curvature in Conjunction with Adaptive Sampling: Theoretical Results and a Practical Algorithm
Albert S. Berahas, Raghu Bollapragada, Wanping Dong
In this paper, we propose algorithms that exploit negative curvature for solving noisy nonlinear nonconvex unconstrained optimization problems. We consider both deterministic and s…
Modified Line Search Sequential Quadratic Methods for Equality-Constrained Optimization with Unified Global and Local Convergence Guarantees
Albert S. Berahas, Raghu Bollapragada, Jiahao Shi
In this paper, we propose a method that has foundations in the line search sequential quadratic programming paradigm for solving general nonlinear equality constrained optimization…
Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients
Sachin Garg, Albert S. Berahas, Michał Dereziński
We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch s…
A Flexible Gradient Tracking Algorithmic Framework for Decentralized Optimization
Albert S. Berahas, Raghu Bollapragada, Shagun Gupta
In decentralized optimization over networks, each node in the network has a portion of the global objective function and the aim is to collectively optimize this function. Gradient…
Non-Uniform Smoothness for Gradient Descent
Albert S. Berahas, Lindon Roberts, Fred Roosta
The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning pro…
Adaptive Consensus: A network pruning approach for decentralized optimization
Suhail M. Shah, Albert S. Berahas, Raghu Bollapragada
We consider network-based decentralized optimization problems, where each node in the network possesses a local function and the objective is to collectively attain a consensus sol…
Collaborative and Distributed Bayesian Optimization via Consensus: Showcasing the Power of Collaboration for Optimal Design
Xubo Yue, Raed Al Kontar, Albert S. Berahas +2
Optimal design is a critical yet challenging task within many applications. This challenge arises from the need for extensive trial and error, often done through simulations or run…
Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization
Albert S. Berahas, Raghu Bollapragada, Shagun Gupta
Gradient tracking methods have emerged as one of the most popular approaches for solving decentralized optimization problems over networks. In this setting, each node in the networ…
A Sequential Quadratic Programming Method with High Probability Complexity Bounds for Nonlinear Equality Constrained Stochastic Optimization
Albert S. Berahas, Miaolan Xie, Baoyu Zhou
A step-search sequential quadratic programming method is proposed for solving nonlinear equality constrained stochastic optimization problems. It is assumed that constraint functio…
Gradient Descent in the Absence of Global Lipschitz Continuity of the Gradients
Vivak Patel, Albert S. Berahas
Gradient descent (GD) is a collection of continuous optimization methods that have achieved immeasurable success in practice. Owing to data science applications, GD with diminishin…
An Adaptive Sampling Sequential Quadratic Programming Method for Equality Constrained Stochastic Optimization
Albert S. Berahas, Raghu Bollapragada, Baoyu Zhou
This paper presents a methodology for using varying sample sizes in sequential quadratic programming (SQP) methods for solving equality constrained stochastic optimization problems…
First- and Second-Order High Probability Complexity Bounds for Trust-Region Methods with Noisy Oracles
Liyuan Cao, Albert S. Berahas, Katya Scheinberg
In this paper, we present convergence guarantees for a modified trust-region method designed for minimizing objective functions whose value and gradient and Hessian estimates are c…
Accelerating Stochastic Sequential Quadratic Programming for Equality Constrained Optimization using Predictive Variance Reduction
Albert S. Berahas, Jiahao Shi, Zihong Yi +1
In this paper, we propose a stochastic method for solving equality constrained optimization problems that utilizes predictive variance reduction. Specifically, we develop a method…
Full-low evaluation methods for derivative-free optimization
Albert S. Berahas, Oumaima Sohab, Luis Nunes Vicente
We propose a new class of rigorous methods for derivative-free optimization with the aim of delivering efficient and robust numerical performance for functions of all types, from s…
A Stochastic Sequential Quadratic Optimization Algorithm for Nonlinear Equality Constrained Optimization with Rank-Deficient Jacobians
Albert S. Berahas, Frank E. Curtis, Michael J. O'Neill +1
A sequential quadratic optimization algorithm is proposed for solving smooth nonlinear equality constrained optimization problems in which the objective function is defined by an e…
Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization
Albert Berahas, Frank E. Curtis, Daniel P. Robinson +1
Sequential quadratic optimization algorithms are proposed for solving smooth nonlinear optimization problems with equality constraints. The main focus is an algorithm proposed for…
SONIA: A Symmetric Blockwise Truncated Optimization Algorithm
Majid Jahani, Mohammadreza Nazari, Rachael Tappenden +2
This work presents a new algorithm for empirical risk minimization. The algorithm bridges the gap between first- and second-order methods by computing a search direction that uses…
Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations
Zheng Shi, Nur Sila Gulgec, Albert S. Berahas +2
Discovering the underlying behavior of complex systems is an important topic in many science and engineering disciplines. In this paper, we propose a novel neural network framework…
On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps
Albert S. Berahas, Raghu Bollapragada, Ermin Wei
In this paper, we consider minimizing a sum of local convex objective functions in a distributed setting, where the cost of communication and/or computation can be expensive. We ex…