mlsanityData to 7 Oct 2026

Learning to Optimize Neural Nets

arXiv 1703.00441 ↗First posted 1 Mar 2017cs.LG cs.AI math.OCcited by 41

Not on the map. Why?

Abstract (arXiv)

Learning to Optimize is a recently proposed framework for learning optimization algorithms using reinforcement learning. In this paper, we explore learning an optimization algorithm for training shallow neural nets. Such high-dimensional stochastic optimization problems present interesting challenges for existing reinforcement learning algorithms. We develop an extension that is suited to learning optimization algorithms in this setting and demonstrate that the learned optimization algorithm consistently outperforms other known optimization algorithms even on unseen tasks and is robust to changes in stochasticity of gradients and the neural net architecture. More specifically, we show that an optimization algorithm trained with the proposed method on the problem of training a neural net on MNIST generalizes to the problems of training neural nets on the Toronto Faces Dataset, CIFAR-10 and CIFAR-100.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 5; 2022: 10; 2023: 8; 2024: 6; 2025: 9; 2026: 1.

41 papers.

Sort:

By area:

  1. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  2. 2022Learning to Learn with Generative Models of Neural Network Checkpointscited by 85
  3. 2022Tutorial on amortized optimizationcited by 83
  4. 2022VeLO: Training Versatile Learned Optimizers by Scaling Upcited by 57
  5. 2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
  6. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  7. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  8. 2018Learning a Prior over Intent via Meta-Inverse Reinforcement Learningcited by 36
  9. 2022Practical tradeoffs between memory, compute, and performance in learned optimizerscited by 32
  10. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  11. 2022Symbolic Learning to Optimize: Towards Interpretability and Scalabilitycited by 16
  12. 2024Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Processcited by 11
29 more
  1. 2025QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initializationcited by 11
  2. 2022Learning to Optimize in Model Predictive Controlcited by 10
  3. 2022Amortized Proximal Optimizationcited by 9
  4. 2024Large Language Models for Human-Machine Collaborative Particle Accelerator Tuning through Natural Languagecited by 9
  5. 2023Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Singlecited by 7
  6. 2023Deep Model Predictive Optimizationcited by 7
  7. 2024Learning to optimize with convergence guarantees using nonlinear system theorycited by 7
  8. 2023A Nonstochastic Control Approach to Optimizationcited by 4
  9. 2023Learning To Optimize Quantum Neural Network Without Gradientscited by 4
  10. 2022Learning to Optimize Quasi-Newton Methodscited by 3
  11. 2024Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layerscited by 3
  12. 2025Learning a Zeroth-Order Optimizer for Fine-Tuning LLMscited by 3
  13. 2023Federated Automatic Differentiationcited by 2
  14. 2023Learning to Do or Learning While Doing: Reinforcement Learning and Bayesian Optimisation for Online Continuous Tuningcited by 2
  15. 2025Improving Learning to Optimize Using Parameter Symmetriescited by 2
  16. 2025Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspectivecited by 2
  17. 2025A Semi-amortized Lifted Learning-to-Optimize Masked (SALLO-M) Transformer Model for Scalable and Generalizable Beamformingcited by 2
  18. 2021Efficient Meta Subspace Optimizationcited by 1
  19. 2021Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Designcited by 1
  20. 2022Reinforcement Teachingcited by 1
  21. 2023Subspace Adaptation Prior for Few-Shot Learningcited by 1
  22. 2025MatRL: Provably Generalizable Iterative Algorithm Discovery via Monte-Carlo Tree Searchcited by 1
  23. 2023HUB: Guiding Learned Optimizers with Continuous Prompt Tuningcited by 0
  24. 2024Dynamic Memory Based Adaptive Optimizationcited by 0
  25. 2024A Memetic Algorithm To Find a Hamiltonian Cycle in a Hamiltonian Graphcited by 0
  26. 2025Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learningcited by 0
  27. 2025Optimization Problem Solving Can Transition to Evolutionary Agentic Workflowscited by 0
  28. 2025Thinking Out of the Box: Hybrid SAT Solving by Unconstrained Continuous Optimizationcited by 0
  29. 2026Greedy dynamical meta-learningcited by 0