8 citations · 12 across the 5 of their papers we have counts for
6 papers
Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative
Amartya Mukherjee, Tristan Milne, Kry Yik-Chau Lui +2
Outliers are important for stress-testing algorithms and understanding system behaviour under rare conditions. Despite being commonly described as low-likelihood events, existing g…
An optimal transport analogue of the Rudin Osher Fatemi model and its corresponding multiscale theory
Tristan Milne, Adrian Nachman
We develop a theory for image restoration with a learned regularizer that is analogous to that of Meyer's characterization of solutions of the classical variational method of Rudin…
A new method for determining Wasserstein 1 optimal transport maps from Kantorovich potentials, with deep learning applications
Tristan Milne, Étienne Bilocq, Adrian Nachman
Wasserstein 1 optimal transport maps provide a natural correspondence between points from two probability distributions, and , which is useful in many applications. Availabl…
Trust the Critics: Generatorless and Multipurpose WGANs with Initial Convergence Guarantees
Tristan Milne, Étienne Bilocq, Adrian Nachman
Inspired by ideas from optimal transport theory we present Trust the Critics (TTC), a new algorithm for generative modelling. This algorithm eliminates the trainable generator from…
Wasserstein GANs with Gradient Penalty Compute Congested Transport
Tristan Milne, Adrian Nachman
Wasserstein GANs with Gradient Penalty (WGAN-GP) are a very popular method for training generative models to produce high quality synthetic data. While WGAN-GP were initially devel…
Piecewise Strong Convexity of Neural Networks
Tristan Milne
We study the loss surface of a feed-forward neural network with ReLU non-linearities, regularized with weight decay. We show that the regularized loss function is piecewise strongl…