Newton method over networks is fast up to the statistical precision
A Daneshmand, G Scutari… - International …, 2021 - proceedings.mlr.press
We propose a distributed cubic regularization of the Newton method for solving
(constrained) empirical risk minimization problems over a network of agents, modeled as …
(constrained) empirical risk minimization problems over a network of agents, modeled as …
Parallel and Decentralized Algorithms for Big-Data Optimization Over Networks
A Daneshmand - 2021 - search.proquest.com
Recent decades have witnessed the rise of data deluge generated by heterogeneous
sources, eg, social networks, streaming, marketing services etc., which has naturally created …
sources, eg, social networks, streaming, marketing services etc., which has naturally created …
Efficient and Scalable Optimization Methods for Training Large-Scale Machine Learning Models
M Jahani - 2021 - search.proquest.com
Many important problems in machine learning (ML) and data science are formulated as
optimization problems and solved using optimization algorithms. With the scale of modern …
optimization problems and solved using optimization algorithms. With the scale of modern …