Research map / Optimization / Nonconvex and smooth optimization
An Accelerated DFO Algorithm for Finite-sum Convex Functions
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 ZO-Varag with variance-reduced stochastic updates and accelerated momentum | finite-sum DFO on diabete and ijcnn1 regression tasks · diabete and ijcnn1; logistic regression and ridge regression | convergence rate | Helped |
| use simplified ZO-Katyusha rather than ZO-Varag | finite-sum DFO regression tasks · diabete and ijcnn1; logistic regression and ridge regression | convergence rate | Helped |
| use bar{x}^{s-1} as the pivot instead of tilde{x}^{s-1} (ablation) | ZO-Varag · logistic regression | convergence rate | Helped |
| use bar{x}^{s-1} as the pivot instead of tilde{x}^{s-1} (ablation) | ZO-Varag · ridge regression | convergence rate | Helped |
| increase regularizer strength lambda (ablation) | ZO-Varag · logistic regression and ridge regression | early convergence rate | Helped |
| increase regularizer strength lambda (ablation) | ZO-Varag · logistic regression and ridge regression | final optimization error | Hurt |
Closest papers by meaning
- A Simple Practical Accelerated Method for Finite Sums (NeurIPS 2016 · similarity 0.89)
- A unified variance-reduced accelerated gradient method for convex optimization (NeurIPS 2019 · similarity 0.89)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.88)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · similarity 0.87)
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization (NeurIPS 2025 · similarity 0.87)
- Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints (NeurIPS 2024 · similarity 0.87)
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.