Use when observations are constrained — strictly positive (intensities, rates, concentrations) or bounded in [0, 1] (fractions, probabilities). LogGPOptimizer and LogitGPOptimizer fit a GP on transformed observations and push the posterior back through the inverse link, so predictions and credible intervals stay inside the constrained range. Includes how to get raw posterior samples for histograms.
Use for end-to-end autonomous experiment design with gpCAM. Translates a scientist's description of their measurement into a complete, runnable gpCAM script — useful for replacing raster scans with adaptive sampling, peak-finding, or parameter optimization.
Use for large-scale gpCAM experiments (>10k points up to millions) using sparse compactly-supported kernels and Dask distributed computing for exact GP computation at scale.
Use when designing custom acquisition functions for gpCAM that encode experimental priorities — exploration vs exploitation balance, multi-objective targets, constrained search regions, cost-aware moves, UCB/LCB, or probability-of-improvement criteria.
Use when modeling the real expense of moving between gpCAM measurement points — motor travel time, settling, directional costs, sample damage, beam time, or zone-based penalties.
Use when designing or composing custom kernel (covariance) functions for gpCAM that encode domain knowledge — smoothness, periodicity, symmetry, anisotropy, or non-Euclidean input spaces.
Use for multi-output, vector-valued, or function-valued gpCAM experiments using fvGPOptimizer — useful when a single measurement returns multiple correlated quantities (e.g., spectra, multi-channel detectors).
Use when modeling position-dependent, heteroscedastic, or otherwise structured noise in gpCAM — e.g., detector characteristics, count-rate-dependent variance, or non-uniform measurement uncertainty.