Sökning: "Anderson acceleration"

Hittade 2 avhandlingar innehållade orden Anderson acceleration.

1. 1. Scalable Optimization Methods for Machine Learning : Acceleration, Adaptivity and Structured Non-Convexity

   Författare :Vien Van Mai; Mikael Johansson; John Duchi; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Large-scale optimization; Anderson acceleration; first-order methods; stochastic optimization; momentum; gradient clipping; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis aims at developing efficient optimization algorithms for solving large-scale machine learning problems. To cope with the increasing scale and complexity of such models, we focus on first-order and stochastic methods in which updates are carried out using only (noisy) information about function values and (sub)gradients. LÄS MER

3. 2. Large-Scale Optimization With Machine Learning Applications

   Författare :Vien Van Mai; Mikael Johansson; Alexandre d'Aspremont; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Optimization algorithms; Anderson acceleration; finite-sum; first-order methods; Optimization and Systems Theory; Optimeringslära och systemteori; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis aims at developing efficient algorithms for solving some fundamental engineering problems in data science and machine learning. We investigate a variety of acceleration techniques for improving the convergence times of optimization algorithms. LÄS MER