Self-Concordant Analysis of Frank-Wolfe Algorithms
arXiv:2002.04320
Abstract
Projection-free optimization via different variants of the Frank-Wolfe (FW), a.k.a. Conditional Gradient method has become one of the cornerstones in optimization for machine learning since in many cases the linear minimization oracle is much cheaper to implement than projections and some sparsity needs to be preserved. In a number of applications, e.g. Poisson inverse problems or quantum state tomography, the loss is given by a self-concordant (SC) function having unbounded curvature, implying absence of theoretical guarantees for the existing FW methods. We use the theory of SC functions to provide a new adaptive step size for FW methods and prove global convergence rate O(1/k) after k iterations. If the problem admits a stronger local linear minimization oracle, we construct a novel FW method with linear convergence rate for SC functions.
arXiv commentProceedings of the 37th International Conference on Machine Learning (ICML2020)
References in corpus (5)
- The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle
- Composite Self-Concordant Minimization
- A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions
- A Newton Frank-Wolfe Method for Constrained Self-Concordant Minimization
- Beyond Least-Squares: Fast Rates for Regularized Empirical Risk Minimization through Self-Concordance