Research map / Probabilistic and scientific modeling / Bayesian optimization
OPT-GAN: A Broad-Spectrum Global Optimizer for Black-Box Problems by Learning Distribution
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 OPT-GAN instead of traditional optimizers | Black-box benchmarks from COCO · COCO test problems | average rank | Helped |
| Use OPT-GAN instead of other neural-network optimizers | Black-box benchmarks from COCO · COCO test problems | fitness | Helped |
| Use OPT-GAN instead of competing optimizers | NEEP symbolic regression · NEEP datasets | fitness | Helped |
| Use OPT-GAN instead of competing optimizers | Frequency Modulated Sounds Parameter Identification · FMSPI | fitness | Helped |
| Use OPT-GAN rather than a Gaussian-prior optimizer | Black-box optimization · Sphere | optimization performance | Hurt |
| Use OPT-GAN rather than CMA-ES | Black-box optimization · 10D Lunacek bi-Rastrigin | optimization performance | Hurt |
| Use OPT-GAN rather than PSO | Black-box optimization · 2D Shifted and Rotated Weierstrass; 10D Michalewicz | optimization performance | Hurt |
| Balance exploration and exploitation with OPT-GAN | Neural-network black-box optimizers · COCO multi-modal problems | fitness | Helped |
| Use OPT-GAN rather than EGL | NEEP symbolic regression · NEEP datasets | fitness | Helped |
| Use OPT-GAN rather than CMA-ES | Black-box optimization · COCO benchmarks with weaker Gaussian trend | average rank | Helped |
| Use OPT-GAN rather than BoRisk | Black-box optimization · COCO test problems | average rank | Mixed |
Closest papers by meaning
- TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN (ICLR 2018 · similarity 0.88)
- A Convergent and Dimension-Independent Min-Max Optimization Algorithm (ICML 2022 · similarity 0.87)
- A Variational Inequality Perspective on Generative Adversarial Networks (ICLR 2019 · similarity 0.87)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.86)
- HVAdam: A Full-Dimension Adaptive Optimizer (AAAI 2025 · similarity 0.86)
- Neuroevolution of a Multi-Generator GAN (Student Abstract) (AAAI 2024 · similarity 0.86)
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.