Research map / Optimization / Optimizers
Differentiable Convex Optimization Layers
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 CVXPY 1.1 DPP/ASA canonicalization instead of CVXPY 1.0.23 | CVXPY canonicalization · Logistic regression | canonicalization time: 18.9 $\pm$ 1.75 -> 1.49 $\pm$ 0.02 | Helped |
| Use CVXPY 1.1 DPP/ASA canonicalization instead of CVXPY 1.0.23 | CVXPY canonicalization · Stochastic control | canonicalization time: 12.5 $\pm$ 0.72 -> 1.39 $\pm$ 0.02 | Helped |
| Use the differentiable layer to learn the control-Lyapunov policy parameters | ADP policy for stochastic control · Stochastic control numerical example | average cost: roughly 40% | Helped |
| Use the proposed layer rather than qpth | Batched QP solving · Sparse QP | execution time: roughly 5 times faster | Helped |
| Use the proposed layer rather than qpth | Batched QP solving · Dense QP | execution time | No clear effect |
Closest papers by meaning
- BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning (NeurIPS 2024 · similarity 0.89)
- Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning (ICLR 2024 · similarity 0.88)
- Near-Optimal Solutions of Constrained Learning Problems (ICLR 2024 · similarity 0.86)
- LPGD: A General Framework for Backpropagation through Embedded Optimization Layers (ICML 2024 · similarity 0.86)
- Learning Provably Improves the Convergence of Gradient Descent (NeurIPS 2025 · similarity 0.85)
- A Differentiable Interior-Point Method in Single Precision (NeurIPS 2026 · similarity 0.85)
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.