🏢 University of Bristol
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
·1434 words·7 mins·
loading
·
loading
Machine Learning
Deep Learning
🏢 University of Bristol
Deep kernel machines now achieve 94.5% accuracy on CIFAR-10, matching neural networks, by using stochastic kernel regularization to improve generalization.
Conditional Outcome Equivalence: A Quantile Alternative to CATE
·2270 words·11 mins·
loading
·
loading
AI Theory
Causality
🏢 University of Bristol
Researchers introduce the Conditional Quantile Comparator (CQC) for analyzing heterogeneous treatment effects, offering an improved approach by combining the strengths of CATE and CQTE while overcomin…