Sökning: "First-Order Methods"

Visar resultat 1 - 5 av 143 avhandlingar innehållade orden First-Order Methods.

1. 1. Efficient and Flexible First-Order Optimization Algorithms

   Författare :Hamed Sadeghi; Institutionen för reglerteknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Monotone Inclusion; Convex Optimization; First-Order Methods; Fixed-Point Iterations; Forward–Backward Splitting; Primal–Dual Algorithm;

   Sammanfattning : Optimization problems occur in many areas in science and engineering. When the optimization problem at hand is of large-scale, the computational cost of the optimization algorithm is a main concern. LÄS MER

3. 2. First-Order Algorithms for Communication Efficient Distributed Learning

   Författare :Sarit Khirirat; Mikael Johansson; Martin Jaggi; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Communication efficient learning; Optimization algorithms; Quantization; Error compensation; First-order algorithms; Stochastic gradient descent; Tillämpad matematik och beräkningsmatematik; Applied and Computational Mathematics; Optimeringslära och systemteori; Optimization and Systems Theory; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : Technological developments in devices and storages have made large volumes of data collections more accessible than ever. This transformation leads to optimization problems with massive data in both volume and dimension. LÄS MER

4. 3. Automated Theorem Proving in a First-Order Logic with First class Boolean Sort

   Författare :Evgenii Kotelnikov; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; first-order logic; program analysis; program verification; TPTP; automated theorem proving; Vampire;

   Sammanfattning : Automated theorem proving is one of the central areas of computer mathematics. It studies methods and techniques for establishing validity of mathematical problems using a computer. The problems are expressed in a variety of formal logics, including first-order logic. LÄS MER

5. 4. Convergence Analysis and Improvements for Projection Algorithms and Splitting Methods

   Författare :Mattias Fält; Institutionen för reglerteknik; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; First-order methods; Convex Optimization; Nonsmooth Optimization; Large-scale Optimization; Iterative Methods; Douglas-Rachford splitting; Line Search;

   Sammanfattning : Non-smooth convex optimization problems occur in all fields of engineering. A common approach to solving this class of problems is proximal algorithms, or splitting methods. These first-order optimization algorithms are often simple, well suited to solve large-scale problems and have a low computational cost per iteration. LÄS MER

7. 5. 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