Learning to Optimize by Differentiable Programming
cs.MS, cs.LG, math.OC
Submitted: 2026-01-23
Updated: 2026-08-30
Code: https://github.com/convexsoft/diffprog
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Differentiating through Log-Log Convex Programs
- OptiMUS: Optimization Modeling Using MIP Solvers and large language models
- On the Differentiability of the Solution to Convex Optimization Problems
- The Elements of Differentiable Programming
- Differentiable programming across the PDE and Machine Learning barrier
- cuDNN: Efficient Primitives for Deep Learning
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- TensorFlow Distributions
- Training verified learners with learned verifiers
- Profiling Apple Silicon Performance for ML Training
- On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
- A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
- Learning Constrained Optimization with Deep Augmented Lagrangian Methods
- End-to-End Constrained Optimization Learning: A Survey
- DeepOPF-U: A Unified Deep Neural Network to Solve AC Optimal Power Flow in Multiple Networks
- MPAX: Mathematical Programming in JAX
- Randomized Automatic Differentiation
- An overview of gradient descent optimization algorithms
- Differentiable Programming for Differential Equations: A Review
- Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
Related papers
- Scen-Opt: A Scenario Optimization Toolbox for Data-Driven Convex Programming
- The Pauli Lightcone: Information-Theoretic Error Mitigation Beyond the Autocorrelation
- FP8 is All You Need (Part 2): Full-FP64 3-D FFT on FP8-Generation Tensor CoresThe Integer-Epilogue Wall and the Minimal Hardware That Would Remove It
- GRADSOLVE: fast exact gradients for ODE ensembles on GPUs
- Tensor Network Kernel Machines: A JAX Framework for Machine Learning and Nonlinear System Identification