Research map / Optimization / Nonconvex and smooth optimization
Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization
Dongruo Zhou, Quanquan Gu
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 |
|---|---|---|---|
| Replace full high-order derivative recomputation with a single-point Taylor expansion estimator (OP-TE) around a reference point | stochastic high-order method for nonconvex finite-sum · theory, ε-stationary point | IHO oracle complexity dependence on n: n^(3p-1)/(3p) vs HR's n | Improved |
| Two-point Taylor expansion gradient estimator (TP-TE) with batch size 1 (m=n) | stochastic high-order method for nonconvex finite-sum · theory, ε-stationary point | IHO oracle complexity dependence on n: n^(2p-1)/(2p) vs OP-TE n^(3p-1)/(3p) | Improved |
| Use stochastic Taylor-based estimators instead of semi-stochastic Hessian estimators (dimension-free error bounds) | second-order (p=2) finite-sum methods · theory, ε-stationary point | dependence on dimension d: removes log d factor | Improved |
Closest papers by meaning
- Lower Bounds for Smooth Nonconvex Finite-Sum Optimization (ICML 2019 · similarity 0.92)
- Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization (NeurIPS 2021 · similarity 0.91)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.90)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.89)
- Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness (ICLR 2025 · similarity 0.89)
- Sample complexity of stochastic optimization with integer variables (NeurIPS 2026 · 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.
