arXiv Machine Learning
Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 24
Constrained Variable Projection for Structured Problems
arXiv:2606. 23939v1 Announce Type: cross Abstract: Variable projection is a classical technique for separable nonlinear least-squares problems, in which variables that enter linearly are eliminated exactly, yielding a reduced nonlinear problem.
arXiv Machine Learning
Jul 2
Towards Weaker Variance Assumptions for Stochastic Optimization
arXiv:2504. 09951v2 Announce Type: replace-cross Abstract: We revisit a classical assumption for analyzing stochastic gradient algorithms where the squared norm of the stochastic subgradient (or the variance for smooth problems) is allowed to grow as fast as the squared norm of the optimization variable.
arXiv Machine Learning
3d ago
Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe Estimator
arXiv:2609.15723v1 Announce Type: new Abstract: Traditional variance reduction methods (e.g., SPIDER, SARAH, STORM) have been extensively investigated for improving the convergence rates of stochasti...
arXiv Machine Learning
Jun 24
Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum
arXiv:2406. 13041v3 Announce Type: replace Abstract: Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ sample complexity to find an $\varepsilon$-stationary point.
arXiv Machine Learning
Jul 23
Online Optimization of Difference-of-Convex Compositions with Smooth Mappings
arXiv:2607. 19553v1 Announce Type: cross Abstract: We study online optimization for a broad class of structured non-convex non-smooth problems where each loss is a composition of a difference-of-convex function with a smooth mapping, and the feasible region is defined by constraint functions of the same kind.
arXiv Machine Learning
Jun 5
Learning to optimize with guarantees: a complete characterization of linearly convergent algorithms
arXiv:2508. 00775v2 Announce Type: replace-cross Abstract: The design of many classical optimization algorithms is driven by the certification of linear convergence rates over classes of optimization problems.