Výsledky vyhľadávania - "Bollapragada, Raghu"

A Retrospective Approximation Approach for Smooth Stochastic Optimization.

Autori: Newton, David Bollapragada, Raghu Pasupathy, Raghu a ďalší

Zdroj: Mathematics of Operations Research; Aug2025, Vol. 50 Issue 3, p2301-2332, 32p

Predmety: STOCHASTIC programming, MATHEMATICAL optimization, DETERMINISTIC algorithms, STATISTICAL accuracy, RETROSPECTIVE studies, NONLINEAR functions, ITERATIVE methods (Mathematics), COMPUTATIONAL complexity

Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization.

Autori: Berahas, Albert S. Bollapragada, Raghu Gupta, Shagun

Zdroj: Journal of Optimization Theory & Applications; Dec2024, Vol. 203 Issue 3, p2954-2987, 34p

Predmety: MATHEMATICAL optimization, CLASSIFICATION, NEIGHBORS

ADAPTIVE CONSENSUS: A NETWORK PRUNING APPROACH FOR DECENTRALIZED OPTIMIZATION.

Autori: SHAH, SUHAIL M. BERAHAS, ALBERT S. BOLLAPRAGADA, RAGHU

Zdroj: SIAM Journal on Optimization; 2024, Vol. 34 Issue 4, p3653-3680, 28p

Predmety: INFORMATION sharing, PROBLEM solving, ALGORITHMS

Constrained and composite optimization via adaptive sampling methods.

Autori: Xie, Yuchen Bollapragada, Raghu Byrd, Richard a ďalší

Zdroj: IMA Journal of Numerical Analysis; Mar2024, Vol. 44 Issue 2, p680-709, 30p

Predmety: SAMPLING methods, CONJUGATE gradient methods, CONSTRAINED optimization

Adaptive sampling quasi-Newton methods for zeroth-order stochastic optimization.

Autori: Bollapragada, Raghu Wild, Stefan M.

Zdroj: Mathematical Programming Computation; Jun2023, Vol. 15 Issue 2, p327-364, 38p

Nonlinear acceleration of momentum and primal-dual algorithms.

Autori: Bollapragada, Raghu Scieur, Damien d'Aspremont, Alexandre

Zdroj: Mathematical Programming; Mar2023, Vol. 198 Issue 1, p325-362, 38p

Predmety: ALGORITHMS, LOGISTIC regression analysis, MATHEMATICAL optimization, LINEAR systems

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

Autori: Berahas, Albert Bollapragada, Raghu Wei, Ermin

Zdroj: IEEE Transactions on Signal Processing; 11/1/2021, p4192-4203, 12p

Predmety: DISTRIBUTED algorithms, CONVEX functions, SET functions, SYMMETRIC matrices, LINEAR programming

Optimization and supervised machine learning methods for fitting numerical physics models without derivatives.

Autori: Bollapragada, Raghu Menickelly, Matt Nazarewicz, Witold a ďalší

Zdroj: Journal of Physics G: Nuclear & Particle Physics; Feb2021, Vol. 48 Issue 2, p1-22, 22p

Predmety: NUCLEAR physics, NUCLEAR models, PHYSICS, ENERGY density, MATHEMATICAL optimization

An investigation of Newton-Sketch and subsampled Newton methods.

Autori: Berahas, Albert S. Bollapragada, Raghu Nocedal, Jorge

Zdroj: Optimization Methods & Software; Aug2020, Vol. 35 Issue 4, p661-680, 20p

Predmety: NEWTON-Raphson method, CONJUGATE gradient methods, DIMENSION reduction (Statistics), DATA reduction, LINEAR equations, LINEAR systems

Exact and inexact subsampled Newton methods for optimization.

Autori: Bollapragada, Raghu Byrd, Richard H Nocedal, Jorge

Zdroj: IMA Journal of Numerical Analysis; Apr2019, Vol. 39 Issue 2, p545-578, 34p

Predmety: LINEAR systems, MATHEMATICAL models, LINEAR differential equations, POSITIVE systems, FINITE element method

Balancing Communication and Computation in Distributed Optimization.

Autori: Berahas, Albert S. Bollapragada, Raghu Keskar, Nitish Shirish a ďalší

Zdroj: IEEE Transactions on Automatic Control; Aug2019, Vol. 64 Issue 8, p3141-3155, 15p

Predmety: SENSOR networks, MACHINE learning, INFORMATION sharing, LINEAR programming, INTERIOR-point methods, DISTRIBUTED algorithms