Learning Hyperparameters via a Data-Emphasized Variational Objective

Ethan Harvey, Mikhail Petrov, Michael C Hughes

TL;DR: By adjusting a term in the evidence lower bound, we enable gradient-based learning of regularization hyperparameters on the full training set, reducing the 88+ hour grid search of past work to under 3 hours.

Abstract: When training large models on limited data, avoiding overfitting is paramount. Common grid search or smarter search methods rely on expensive separate runs for each candidate hyperparameter, while carving out a validation set that reduces available training data. In this paper, we study gradient-based learning of hyperparameters via the evidence lower bound (ELBO) objective from Bayesian variational methods. This avoids the need for any validation set. We focus on scenarios where the model is over-parameterized for flexibility and the approximate posterior is chosen to be Gaussian with isotropic covariance for tractability, even though it cannot match the true posterior. In such scenarios, we find the ELBO prioritizes posteriors that match the prior, leading to severe underfitting. Instead, we recommend a data-emphasized ELBO that upweights the likelihood but not the prior. In Bayesian transfer learning of image and text classifiers, our method reduces the 88+ hour grid search of past work to under 3 hours while delivering comparable accuracy. We further demonstrate how our approach enables efficient yet accurate approximations of Gaussian processes with learnable lengthscale kernels.

Code Dataset Promise: Yes

Code Dataset Url: https://github.com/tufts-ml/data-emphasized-ELBO

Format Confirmation: I agree that I have read and followed the formatting instructions for the camera ready version.

Submission Number: 935