arXiv (All)
open access
Gradient-Only Online Convex Optimization with a Single Quadratic Leader
We study online convex optimization on a bounded Euclidean domain when the learner receives only one subgradient at its prediction and knows neither the horizon, a gradient bound, nor the losses' strong-convexity parameters. We present a scale-invariant algorithm that couples projected adaptive grad
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Acceleration for Affine-coupling problems#1132198
- On the Convergence, Implicit Bias, and Edge of Stability of Gradient Descent in Deep Learning: Reviewing recent progress [Special Issue on the Mathematics of Deep Learning].#489684
- Efficient Gradient Methods for Distributed Saddle Problems#200445
- Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent#1129251
- Near-Optimal Higher-Order Oracle Complexity for Convex--Concave Minimax Optimization#1064790
Record · ID 1154813
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive