Sharpness-aware minimization (SAM) aims to improve the generalisation of gradient-based learning by seeking out flat minima.
It is known that under i.\, i.\, d assumption, even with infinite data, there is a limit to how fine-grained a causal structure we can identify.
In gradient descent, changing how we parametrize the model can lead to drastically different optimization trajectories, giving rise to a surprising range of meaningful inductive biases: identifying sparse classifiers or reconstructing low-rank matrices without explicit regularization.
We present a novel model architecture which leverages deep learning tools to perform exact Bayesian inference on sets of high dimensional, complex observations.
Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition.
Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel algorithm designed to safeguard against catastrophic forgetting in neural networks.
We show that, using this architecture, the amortised MAP inference problem reduces to minimising the cross-entropy between two distributions, similar to training generative models.
This means that the super-resolution (SR) operation is performed in HR space.
Ranked #1 on Video Super-Resolution on Xiph HD - 4x upscaling
We introduce a generalisation of adversarial training, and show how such method can interpolate between maximum likelihood training and our ideal training objective.
Information theoretic active learning has been widely studied for probabilistic models.