Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Bollapragada, Raghu"'
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 problems. The method employs a carefully designed modified line searc
Externí odkaz:
http://arxiv.org/abs/2406.11144
In this paper, we present a novel derivative-free optimization framework for solving unconstrained stochastic optimization problems. Many problems in fields ranging from simulation optimization to reinforcement learning involve settings where only st
Externí odkaz:
http://arxiv.org/abs/2404.11893
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 tracking methods have emerged as a popular alternative for solving su
Externí odkaz:
http://arxiv.org/abs/2312.06814
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 solution that minimizes the sum of all the local functions. A major chall
Externí odkaz:
http://arxiv.org/abs/2309.02626
Autor:
Shah, Suhail M., Bollapragada, Raghu
Decentralized optimization is typically studied under the assumption of noise-free transmission. However, real-world scenarios often involve the presence of noise due to factors such as additive white Gaussian noise channels or probabilistic quantiza
Externí odkaz:
http://arxiv.org/abs/2307.14942
Autor:
Bollapragada, Raghu, Karamanli, Cem, Keith, Brendan, Lazarov, Boyan, Petrides, Socratis, Wang, Jingyi
The primary goal of this paper is to provide an efficient solution algorithm based on the augmented Lagrangian framework for optimization problems with a stochastic objective function and deterministic constraints. Our main contribution is combining
Externí odkaz:
http://arxiv.org/abs/2305.01018
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 network has a portion of the global objective function, and the goal is to c
Externí odkaz:
http://arxiv.org/abs/2303.14289
Simple stochastic momentum methods are widely used in machine learning optimization, but their good practical performance is at odds with an absence of theoretical guarantees of acceleration in the literature. In this work, we aim to close the gap be
Externí odkaz:
http://arxiv.org/abs/2206.07553
This paper presents a methodology for using varying sample sizes in sequential quadratic programming (SQP) methods for solving equality constrained stochastic optimization problems. The first part of the paper deals with the delicate issue of dynamic
Externí odkaz:
http://arxiv.org/abs/2206.00712
Multi-objective optimization (MOO) problems require balancing competing objectives, often under constraints. The Pareto optimal solution set defines all possible optimal trade-offs over such objectives. In this work, we present a novel method for Par
Externí odkaz:
http://arxiv.org/abs/2110.15442