Search Results for author:
Found 9 papers, 7 papers with code
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
The computation necessary for training Transformer-based language models has skyrocketed in recent years.
Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
Likelihood-free inference methods typically make use of a distance between simulated and real data.
Towards Healing the Blindness of Score Matching
Score-based divergences have been widely used in machine learning and statistics applications.
Composite Goodness-of-fit Tests with Kernels
Model misspecification can create significant challenges for the implementation of probabilistic models, and this has led to development of a range of robust methods which directly account for this issue.
Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
Counterfactual explanations (CEs) are a practical tool for demonstrating why machine learning classifiers make particular decisions.
On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
Inducing point Gaussian process approximations are often considered a gold standard in uncertainty estimation since they retain many of the properties of the exact GP and scale to large datasets.
Variational Deterministic Uncertainty Quantification
Building on recent advances in uncertainty quantification using a single deep deterministic model (DUQ), we introduce variational Deterministic Uncertainty Quantification (vDUQ).
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes
We show that the gradient estimates used in training Deep Gaussian Processes (DGPs) with importance-weighted variational inference are susceptible to signal-to-noise ratio (SNR) issues.
Interlocking Backpropagation: Improving depthwise model-parallelism
Motivated by poor resource utilisation in the global setting and poor task performance in the local setting, we introduce a class of intermediary strategies between local and global learning referred to as interlocking backpropagation.
