Projection-Free Adaptive Gradients for Large-Scale Optimization
From MaRDI portal
Publication:6350156
arXiv2009.14114MaRDI QIDQ6350156
Author name not available (Why is that?)
Publication date: 29 September 2020
Abstract: The complexity in large-scale optimization can lie in both handling the objective function and handling the constraint set. In this respect, stochastic Frank-Wolfe algorithms occupy a unique position as they alleviate both computational burdens, by querying only approximate first-order information from the objective and by maintaining feasibility of the iterates without using projections. In this paper, we improve the quality of their first-order information by blending in adaptive gradients. We derive convergence rates and demonstrate the computational advantage of our method over the state-of-the-art stochastic Frank-Wolfe algorithms on both convex and nonconvex objectives. The experiments further show that our method can improve the performance of adaptive gradient algorithms for constrained optimization.
Has companion code repository: https://github.com/ZIB-IOL/StochasticFrankWolfe
This page was built for publication: Projection-Free Adaptive Gradients for Large-Scale Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6350156)
