26 citations · 38 across the 8 of their papers we have counts for
8 papers
Riemannian Residual Neural Networks
Isay Katsman, Eric Ming Chen, Sidhanth Holalkere +4
Recent methods in geometric deep learning have introduced various neural networks to operate over data that lie on Riemannian manifolds. Such networks are often necessary to learn…
Denoising Diffusion Bridge Models
Linqi Zhou, Aaron Lou, Samar Khanna +1
Diffusion models are powerful generative models that map noise to data using stochastic processes. However, for many applications such as image editing, the model input comes from…
Reflected Diffusion Models
Aaron Lou, Stefano Ermon
Score-based diffusion models learn to reverse a stochastic differential equation that maps data to noise. However, for complex tasks, numerical error can compound and result in hig…
Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks
Tolga Birdal, Aaron Lou, Leonidas Guibas +1
Disobeying the classical wisdom of statistical learning theory, modern deep neural networks generalize well even though they typically contain millions of parameters. Recently, it…
Equivariant Manifold Flows
Isay Katsman, Aaron Lou, Derek Lim +3
Tractably modelling distributions over manifolds has long been an important goal in the natural sciences. Recent work has focused on developing general machine learning models to l…
Neural Manifold Ordinary Differential Equations
Aaron Lou, Derek Lim, Isay Katsman +4
To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces. In this paper, we study normalizing flows on…
Differentiating through the Fréchet Mean
Aaron Lou, Isay Katsman, Qingxuan Jiang +3
Recent advances in deep representation learning on Riemannian manifolds extend classical deep learning operations to better capture the geometry of the manifold. One possible exten…
Adversarial Example Decomposition
Horace He, Aaron Lou, Qingxuan Jiang +3
Research has shown that widely used deep neural networks are vulnerable to carefully crafted adversarial perturbations. Moreover, these adversarial perturbations often transfer acr…