Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

While the choice of prior is one of the most critical parts of the Bayesian inference workflow,
recent Bayesian deep learning models have often fallen back on vague priors, such as …

We perform a careful, thorough, and large scale empirical study of the correspondence
between wide neural networks and kernel methods. By doing so, we resolve a variety of …

Isotropic Gaussian priors are the de facto standard for modern Bayesian neural network
inference. However, it is unclear whether these priors accurately reflect our true beliefs …

Convolutions encode equivariance symmetries into neural networks leading to better
generalisation performance. However, symmetries provide fixed hard constraints on the …

Data augmentation is commonly applied to improve performance of deep learning by
enforcing the knowledge that certain transformations on the input preserve the output …

The linearised Laplace method for estimating model uncertainty has received renewed
attention in the Bayesian deep learning community. The method provides reliable error bars …

Selecting hyperparameters in deep learning greatly impacts its effectiveness but requires
manual effort and expertise. Recent works show that Bayesian model selection with Laplace …

Parameter-efficient fine-tuning (PEFT) has emerged as a new paradigm for cost-efficient fine-
tuning of large language models (LLMs), with low-rank adaptation (LoRA) being a widely …

Parameter-space regularization in neural network optimization is a fundamental tool for
improving generalization. However, standard parameter-space regularization methods …