A Deterministic Nonsmooth Frank Wolfe Algorithm with Coreset Guarantees
This provides a scalable, deterministic method for various ML optimization problems, offering incremental improvements in efficiency for large datasets.
The paper tackles the problem of minimizing nonsmooth convex objectives in machine learning by introducing a deterministic Frank-Wolfe algorithm with coreset guarantees, achieving approximate solutions with time complexity independent of input size for problems like 1-median and Sparse PCA, and showing practical computational advantages in experiments.
We present a new Frank-Wolfe (FW) type algorithm that is applicable to minimization problems with a nonsmooth convex objective. We provide convergence bounds and show that the scheme yields so-called coreset results for various Machine Learning problems including 1-median, Balanced Development, Sparse PCA, Graph Cuts, and the $\ell_1$-norm-regularized Support Vector Machine (SVM) among others. This means that the algorithm provides approximate solutions to these problems in time complexity bounds that are not dependent on the size of the input problem. Our framework, motivated by a growing body of work on sublinear algorithms for various data analysis problems, is entirely deterministic and makes no use of smoothing or proximal operators. Apart from these theoretical results, we show experimentally that the algorithm is very practical and in some cases also offers significant computational advantages on large problem instances. We provide an open source implementation that can be adapted for other problems that fit the overall structure.