Research map / Bandits and online learning / Online convex optimization and games
The Lazy Online Subgradient Algorithm is Universal on Strongly Convex Domains
Daron Anderson, Douglas J. Leith
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| decrease exponent r of the mean cost vector (towards uniform cost direction) under noise type 1 | Online Lazy Gradient Descent · l_1.5 unit ball | average pseudo-regret | Hurt |
| increase r under noise type 2 (noise on last component) | Online Lazy Gradient Descent · l_1.5 unit ball | average pseudo-regret | Hurt |
| increase dimension d (r=0, noise type 1) | Online Lazy Gradient Descent · l_p ball | average pseudo-regret | Improved |
| increase dimension d (r=8, noise type 2) | Online Lazy Gradient Descent · l_p ball | average pseudo-regret | Hurt |
| decrease p towards 1 (less curvature) | Online Lazy Gradient Descent · l_p ball worst cases | average pseudo-regret | Hurt |
| use Greedy Gradient Descent update instead of Lazy | Online Gradient Descent · Euclidean unit ball | worst-case regret growth | Hurt |
| vary noise type (1,2,3) on Schatten ball | Online Lazy Gradient Descent · Schatten unit ball | average pseudo-regret | No clear effect |
| increase d / decrease p on Schatten ball | Online Lazy Gradient Descent · Schatten unit ball | average pseudo-regret | Mixed |
Closest papers by meaning
- Parameter-free Regret in High Probability with Heavy Tails (NeurIPS 2022 · similarity 0.90)
- Efficient online algorithms for fast-rate regret bounds under sparsity (NeurIPS 2018 · similarity 0.89)
- Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness (NeurIPS 2022 · similarity 0.89)
- Universal Online Convex Optimization with $1$ Projection per Round (NeurIPS 2024 · similarity 0.89)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · similarity 0.89)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
