Riccardo Doyle

Riccardo Doyle

Several novel frameworks for hyperparameter search have emerged in the last decade, but most rely on strict, often normal, distributional assumptions, limiting search model flexibility. This paper proposes a novel optimization framework based on upper confidence bound sampling of conformal confidence intervals, whose weaker assumption of exchangeability enables greater choice of search model architectures. Several such architectures were explored and benchmarked on hyperparameter search of random forests and convolutional neural networks, displaying satisfactory interval coverage and superior tuning performance to random search.

Riccardo Doyle

Bayesian hyperparameter optimization relies heavily on Gaussian Process (GP) surrogates, due to robust distributional posteriors and strong performance on limited training samples. GPs however underperform in categorical hyperparameter environments or when assumptions of normality, heteroskedasticity and symmetry are excessively challenged. Conformalized quantile regression can address these estimation weaknesses, while still providing robust calibration guarantees. This study builds upon early work in this area by addressing feedback covariate shift in sequential acquisition and integrating a wider range of surrogate architectures and acquisition functions. Proposed algorithms are rigorously benchmarked against a range of state of the art hyperparameter optimization methods (GP, TPE and SMAC). Findings identify quantile surrogate architectures and acquisition functions yielding superior performance to the current quantile literature, while validating the beneficial impact of conformalization on calibration and search performance.