Research map / Optimization / Optimizers
Provably Correct Automatic Sub-Differentiation for Qualified Programs
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 randomized directional branch selection with constraint-qualified library functions and reverse-mode differentiation | Automatic Subdifferentiation · Programs satisfying the stated assumptions | runtime factor: 6*Runtime^*(f;x) | Helped |
| Use the presented algorithm with a reverse-mode pass for each library function | Automatic Subdifferentiation · Programs satisfying the stated assumptions | runtime factor: factor of 10 | Mixed |
Closest papers by meaning
- On the complexity of nonsmooth automatic differentiation (ICLR 2023 · similarity 0.87)
- Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators (NeurIPS 2024 · similarity 0.84)
- How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization (ICML 2024 · similarity 0.84)
- Automatic Differentiation of Optimization Algorithms with Time-Varying Updates (ICML 2025 · similarity 0.84)
- Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency (NeurIPS 2026 · similarity 0.83)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.83)
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.