Blended Conditonal Gradients

By Gábor Braun, Sebastian Pokutta, Dan Tu, Stephen J. Wright. 2019

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. Sebastian Pokutta
2. Thomas Kerdreux
3. Francesco Rinaldi
4. Damiano Zeffiro
5. Alejandro Carderera
6. Damien Scieur
7. Lewis Liu
8. Simon Lacoste-Julien

Citations in the corpus

• Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets (2020, background): “(Braun et al., 2017; Kerdreux et al., 2018; Braun et al., 2019; Combettes & Pokutta, 2020; Carderera & Pokutta, 2020; Mortagy et al., 2020; Combettes et al., 2020; Bomze et al., 2021)) and in their theoretical understanding.”
• Second-order Conditional Gradients (2020, methodology): “Although projecting into any (cid:96) 1 ball has complexity O ( n ) , and so projections are cheap, this feasible region is often used to compare the performance of projection-free algorithms between each other (see Lacoste-Julien & Jaggi (2015); Rao et al. (2015); Braun et al. (2019)).”
• A unifying framework for the analysis of projection-free first-order methods under a sufficient slope condition (2020, background): “Different approaches to avoid computations of those solutions have been discussed in [12] , [11] for convex optimization over polytopes.”