An extension of the frank and Wolfe method of feasible directions

By Charles A. Holloway. 1974

Subfields: Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

1. Simon Lacoste-Julien
2. Jean-Baptiste Alayrac
3. Martin Jaggi
4. Anton Osokin
5. Puneet Kumar Dokania
6. Isabella Lukasewitz
7. Peter Richtárik
8. Francis R. Bach

Citations in the corpus

• Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs (2016, methodology): “Caching the results of the max oracle implements this idea by reusing the previous calls of the max oracle to store potentially promising corners.”
• On the Global Linear Convergence of Frank-Wolfe Optimization Variants (2015, methodology): “Holloway [14] also argued that FCFW had an asymptotic linear convergence based on the flawed argument of Wolfe [34].”
• Blended Conditional Gradients: the unconditioning of conditional gradients (2018, unknown): “BCG is quite distinct from the fully-corrective Frank–Wolfe algorithm (FCFW) (see, for example, (Holloway, 1974; Lacoste-Julien & Jaggi, 2015)).”