71 citations · 218 across the 16 of their papers we have counts for
6 papers · 1 filter
Transflow Learning: Repurposing Flow Models Without Retraining
Andrew Gambardella, Atılım Güneş Baydin, Philip H. S. Torr
It is well known that deep generative models have a rich latent space, and that it is possible to smoothly manipulate their outputs by traversing this latent space. Recently, archi…
Probabilistic Super-Resolution of Solar Magnetograms: Generating Many Explanations and Measuring Uncertainties
Xavier Gitiaux, Shane A. Maloney, Anna Jungbluth +7
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific do…
Attention for Inference Compilation
William Harvey, Andreas Munk, Atılım Güneş Baydin +2
We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation o…
Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo
Adam D. Cobb, Atılım Güneş Baydin, Andrew Markham +1
We introduce a recent symplectic integration scheme derived for solving physically motivated systems with non-separable Hamiltonians. We show its relevance to Riemannian manifold H…
Probabilistic Surrogate Networks for Simulators with Unbounded Randomness
Andreas Munk, Berend Zwartsenberg, Adam Ścibior +5
We present a framework for automatically structuring and training fast, approximate, deep neural surrogates of stochastic simulators. Unlike traditional approaches to surrogate mod…
Alpha MAML: Adaptive Model-Agnostic Meta-Learning
Harkirat Singh Behl, Atılım Güneş Baydin, Philip H. S. Torr
Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks…