Gaussian Processes and Bayesian Inference

The paper establishes the relationship between Gaussian process priors and regularized regression in sequence-to-function mapping, showing how to construct regularizers that correspond to explicit Gaussian process priors and characterize implicit function space priors.

The paper develops a Bayesian method using Gaussian Processes to map diffusion coefficients continuously across membranes from particle trajectories without data binning.

This paper introduces a Gaussian process multi-class decoder (GPMD) for neural decoding, achieving state-of-the-art accuracy across species and demonstrating the importance of correlation structure.

The paper develops variational log-Gaussian point-process methods to efficiently calculate spatial statistics for grid cells in large environments using Gaussian processes.

This paper develops a scalable Gaussian process model for predicting neural responses to natural images, outperforming deep neural networks on small datasets and enabling efficient model learning and comparison.

The paper introduces a scalable variational inference method for estimating low-rank spatio-temporal receptive fields in neural data, showing improved performance over existing estimators.

This paper introduces a warped Bayesian Linear Regression framework for normative modelling, improving scalability and non-Gaussian distribution handling in neuroimaging data.

This paper shows that Gaussian Process Regression uncertainty is not relevant for quantifying cohort heterogeneity in normative modeling.

The paper develops a Bayesian statistical pipeline for analyzing two-photon imaging data using Gaussian Process Regression to infer neural activity and guide experimental design.

This paper introduces branch-recombinant Gaussian processes (B-RGPs) to analyze branching and recombination in biological time series, demonstrating their application to gene expression data in Arabidopsis thaliana.