Home▸AI & Machine Learning▸Designing Hyperparameter Search Spaces

🧠 Designing Hyperparameter Search Spaces

A 3D validation-score landscape you can search with grid, log-uniform or naive linear sampling — see how search-space width and scaling choices change how much of the optimum you actually find.

AI & Machine Learning3DAdvanced60 FPS

A 3D validation-score landscape over learning rate and dropout that you search with grid, log-uniform or naive linear sampling — watch how search-space width, centring and scale choices change how much of the optimum your budget actually reaches.

🔬 What It Demonstrates

The landscape has one narrow high-score ridge flanked by underfitting (learning rate too low) and instability (learning rate too high). Log-uniform sampling covers this ridge efficiently; linear-uniform sampling wastes most of its budget near the high end of the range.

🎮 How to Use

Pick a sampling strategy, set your sample budget and search width, then try biasing the box toward high learning rates to see a mis-scoped search space clip the optimum out entirely. The indigo box always marks your defined bounds.

💡 Did You Know?

Bergstra & Bengio (2012) showed random search often beats grid search in high dimensions — but that advantage only holds if the search space's ranges and scaling are chosen sensibly in the first place.

⚙ Under the hood

A 3D validation-score landscape you can search with grid, log-uniform or naive linear sampling — see how search-space width and scaling choices change how much of the optimum you actually find.

machine learninghyperparameter optimizationsearch spacegrid searchlog uniform samplingartificial intelligenceThree.js

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install