Research map / Optimization / Optimizers
The ensmallen library for flexible numerical optimization
Ryan R. Curtin, Marcus Edel, Rahul Ganesh Prabhu, Suryoday Basak, Zhihao Lou, Conrad Sanderson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 ensmallen instead of SciPy for L-BFGS linear regression | L-BFGS linear regression · d: 100, n: 100k | runtime (s): 0.2247s -> 0.1460s | Improved |
| use ensmallen instead of PyTorch autodiff L-BFGS | linear regression · d: 1k, n: 100k | runtime (s): 5.6041s -> 1.4011s | Improved |
| use ensmallen instead of bfgsmin() from Octave | linear regression · d: 1k, n: 100k | runtime (s): 9710.6750s -> 1.4011s | Improved |
| use ensmallen instead of Optim.jl | linear regression · d: 1k, n: 100k | runtime (s): 1.3985s vs 1.4011s | No clear effect |
| use ensmallen instead of TensorFlow | logistic regression · MNIST | runtime (s): 9.3662s -> 0.6546s | Improved |
| use ensmallen instead of PyTorch | logistic regression · font | runtime (s): 59.0194s -> 6.1678s | Improved |
| use ensmallen instead of SciPy | logistic regression · MNIST | runtime (s): 0.8101s -> 0.6546s | Improved |
| use ensmallen instead of Autograd | logistic regression · pokerhand | runtime (s): 2.6005s -> 0.5186s | Improved |
| use ensmallen instead of bfgsmin() | logistic regression · MNIST | runtime (s): 539.1358s -> 0.6546s | Improved |
| use ensmallen instead of Optim.jl | logistic regression · isolet | runtime (s): 0.1214s -> 0.0510s | Improved |
Closest papers by meaning
- OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling (ICLR 2025 · similarity 0.84)
- MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling (NeurIPS 2026 · similarity 0.83)
- Adaptively Incorporating Directional Hints into Zeroth-Order Optimization (NeurIPS 2026 · similarity 0.83)
- Adaptive Partitioning Schemes for Optimistic Optimization (ICML 2025 · similarity 0.83)
- OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations (NeurIPS 2024 · similarity 0.83)
- Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion (ICML 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.
