April 16, 2024, 4:45 a.m. | Severin Maier, Camille Castera, Peter Ochs

cs.LG updates on arXiv.org arxiv.org

arXiv:2311.10053v2 Announce Type: replace-cross
Abstract: We introduce an autonomous system with closed-loop damping for first-order convex optimization. While, to this day, optimal rates of convergence are almost exclusively achieved by non-autonomous methods via open-loop damping (e.g., Nesterov's algorithm), we show that our system, featuring a closed-loop damping, exhibits a rate arbitrarily close to the optimal one. We do so by coupling the damping and the speed of convergence of the system via a well-chosen Lyapunov function. By discretizing our system …

abstract algorithm arxiv autonomous convergence cs.lg loop math.ds math.oc near optimization rate show type via

Seeking Developers and Engineers for AI T-Shirt Generator Project

@ Chevon Hicks | Remote

Software Engineer for AI Training Data (School Specific)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Python)

@ G2i Inc | Remote

Software Engineer for AI Training Data (Tier 2)

@ G2i Inc | Remote

Data Engineer

@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania

GCP Data Engineer

@ Avant Digital | Delhi, DL, India