Journal ArticleDOI
Some comments of Wolfe's `away step'
J Guélat,Patrice Marcotte +1 more
TLDR
It is given a detailed proof, under slightly weaker conditions on the objective function, that a modified Frank-Wolfe algorithm based on Wolfe's ‘away step’ strategy can achieve geometric convergence, provided a strict complementarity assumption holds.Abstract:
We give a detailed proof, under slightly weaker conditions on the objective function, that a modified Frank-Wolfe algorithm based on Wolfe's ‘away step’ strategy can achieve geometric convergence, provided a strict complementarity assumption holds.read more
Citations
More filters
Journal ArticleDOI
Riemannian Optimization via Frank-Wolfe Methods
TL;DR: In this paper , a projection-free Riemannian Frank-Wolfe (RFW) method was proposed to solve geodesically convex and non-convex problems.
Dissertation
Acceleration methods for classic convex optimization Algorithms
TL;DR: This thesis develops practical versions of Conjugate Gradient, which is essentially equivalent to the Heavy Ball method, and Nesterov’s Acceleration for the SMO algorithm, and analyzed two classical momentum-based methods.
Posted Content
Learning Near-optimal Convex Combinations of Basis Models with Generalization Guarantees.
TL;DR: This paper presents some new theoretical insights, and empirical results that demonstrate the effectiveness of the greedy algorithm, which requires little effort in hyper-parameter tuning, and seems to adapt to the underlying complexity of the problem.
Proceedings ArticleDOI
Approximate Vanishing Ideal Computations at Scale
TL;DR: It is proved that the computational complexity of OAVI is not superlinear but linear in the number of samples 𝑚 and polynomial in the numbers of features, making O AVI an attractive preprocessing technique for large-scale machine learning.
Journal ArticleDOI
A Newton Frank–Wolfe method for constrained self-concordant minimization
TL;DR: In this article, the authors developed a new Newton Frank-Wolfe algorithm to solve a class of constrained self-concordant minimization problems using linear minimization oracles (LMO).
References
More filters