Research map / Optimization / Nonconvex and smooth optimization
Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows
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 FxTS-GF instead of Adam or NAG | Optimization of the Rosenbrock function · Rosenbrock function, initial point (0.3,0.8) | convergence speed | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Optimization of the Rosenbrock function · Rosenbrock function, initial point (0.3,0.8) | convergence speed | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · MNIST | training loss | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · MNIST | training accuracy | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · MNIST | test accuracy | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · CIFAR10 | training loss | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · CIFAR10 | training accuracy | Helped |
| Use FxTS(M)-GF instead of Adam or NAG | Neural network training · CIFAR10 | test accuracy | Helped |
Closest papers by meaning
- Finite-Time Convergence in Continuous-Time Optimization (ICML 2020 · similarity 0.89)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · similarity 0.88)
- Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time (NeurIPS 2025 · similarity 0.88)
- Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares (NeurIPS 2025 · similarity 0.88)
- Accelerating Optimization via Differentiable Stopping Time (NeurIPS 2025 · similarity 0.87)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · 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.