Research map / Learning theory and algorithms / Sample complexity
Unifying Width-Reduced Methods for Quasi-Self-Concordant Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 unified width reduction with coupled potentials for quasi-self-concordant losses | Constrained convex optimization · M-q.s.c. losses | linear system solver calls: O(m^{1/2}) to \tilde{O}(m^{1/3}) | Helped |
| Apply width reduction directly to constrained logistic regression | Constrained logistic regression · Logistic regression | linear system solver calls: O(m^{1/3}R\log (m R/\delta)) | Helped |
| Use width-reduced optimization for softmax | Softmax · Softmax | linear system solver calls: \widetilde{O}(m^{1/3}\nu^{-5/3}) | Helped |
Closest papers by meaning
- Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights (NeurIPS 2025 · similarity 0.89)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.87)
- Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings (NeurIPS 2025 · similarity 0.87)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.86)
- Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds (NeurIPS 2024 · similarity 0.86)
- Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient (ICML 2024 · similarity 0.86)
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.