Research map / Learning theory and algorithms / Sample complexity
Unifying lower bounds on prediction dimension of convex surrogates
Jessica Finocchiaro, Rafael Frongillo, Bo Waggoner
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 |
|---|---|---|---|
| Use d-flat containment instead of the feasible subspace dimension bound | Abstain loss lower bound · Abstain loss, 3 labels, uniform distribution | convex consistency dimension lower bound: 0 -> 2 | Improved |
| Use d-flat containment to lower-bound prediction dimension | Abstain loss lower bound · Abstain loss, 3 labels, distribution (1/4, 1/4, 1/2) | convex consistency dimension lower bound: 1 -> 1 | No clear effect |
| Elicit the first two moments and link them to variance | Convex surrogate for variance · Variance estimation | convex elicitation complexity: 2 | Improved |
| Apply the d-flat lower-bound framework to CVaR_α | Convex surrogate for CVaR_α · CVaR_α estimation | convex elicitation complexity lower bound: ≥ 2 | Improved |
Closest papers by meaning
- Quantifying Learning Guarantees for Convex but Inconsistent Surrogates (NeurIPS 2018 · similarity 0.89)
- Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification (NeurIPS 2024 · similarity 0.88)
- A Universal Growth Rate for Learning with Smooth Surrogate Losses (NeurIPS 2024 · similarity 0.87)
- Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer (NeurIPS 2024 · similarity 0.87)
- $H$-Consistency Guarantees for Regression (ICML 2024 · similarity 0.86)
- Consistency Conditions for Differentiable Surrogate Losses (NeurIPS 2025 · similarity 0.85)
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.
