Grid Search Experiment

Search…
Description
A grid search experiment enables users to execute an exhaustive search on a user-defined grid with the SigOpt Platform. This means that you'll need to assign grid (or categorical) values to every parameter as part of the experiment create call.
View a sample grid search experiment implementation in a notebook
See this notebook for a demonstration of how easy grid search is with SigOpt. For more notebook instructions and tutorials, check out our GitHub notebook tutorials repo.​
Python
YAML
sigopt.create_experiment(
  name="Grid search",
  type="grid",
  parameters=[
    dict(
      name="hidden_layer_size",
      type="int",
      grid=[
        32,
        64,
        128,
        256,
        512
      ]
    ),
    dict(
      name="activation_function",
      type="categorical",
      categorical_values=[
        "relu",
        "tanh"
      ]
    )
  ],
  metrics=[
    dict(
      name="holdout_accuracy",
      objective="maximize"
    )
  ],
  parallel_bandwidth=1,
  budget=30
)
name: Grid search
type: grid
parameters:
  - name: hidden_layer_size
    type: int
    grid:
      - 32
      - 64
      - 128
      - 256
      - 512
  - name: activation_function
    type: categorical
    categorical_values:
      - relu
      - tanh
metrics:
  - name: holdout_accuracy
    objective: maximize
parallel_bandwidth: 1
budget: 30
Random Search Experiment
Define and Set Up Parameter Space
Last modified 3mo ago
Copy link