Backend
A Spectral Proximal DC Algorithm with Nonmonotone Line Search and Extrapolation
arXiv cs.NA0 views
arXiv:2608.03465v2 Announce Type: replace-cross Abstract: The paper proposes a novel proximal difference-of-convex (DC) algorithmic framework to solve general nonconvex, nonsmooth optimization problems. The basic pBBDCA method combines Barzilai-Borwein (BB) parameter selection with a nonmonotone directional line search, requiring only one proximal solve per iteration. We also develop two extrapolated variants using restart and safeguarding mechanisms. The global convergence of the proposed framework is rigorously established under the Kurdyka-\L ojasiewicz property. Numerical experiments on the SCAD-regularized least squares problem and graph Ginzburg-Landau image segmentation models demonstrate that the proposed methods achieve highly competitive efficiency and accuracy.
Source:https://arxiv.org/abs/2608.03465PreviousWatch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate ScheduleNextKusner's conjecture on equilateral sets is false
Related posts

Dreame X50 Ultra: designing a Shopify buying journey around fit, bundles and payment conditions
0dev.to JavaScript
Connect Four in 86 lines: how I coded the rules for a multiplayer browser game
0dev.to JavaScript
From Prompt to Production: Architectural Deep‑Dive into MIT’s “How to Make Almost Anything” Framework
0dev.to Rust
PRISM: Preference-based Reward and Uncertainty-Integrated Synthesis Minimization for RTL PPA Optimization
0arXiv cs.SE
The $\alpha$-Limit Problem: Convergence of a Linear Degenerate Interface Transmission Problem
0arXiv cs.NA
Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule
0arXiv stat.ML