6 papers
SURF: Separation via Unsupervised Remixing Flow
Henry Li, Robin Scheibler, Efthymios Tzinis +3
The goal of single-channel source separation is to reconstruct sources given their mixture. In supervised settings where vast amounts of clean source data are available, this c…
Permutation-Invariant Spectral Learning via Dyson Diffusion
Tassilo Schwarz, Cai Dieball, Constantin Kogler +4
Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challenge of having up to such represent…
Metropolis-Adjusted Diffusion Models
Kevin H. Lam, Tyler Farghly, Christopher Williams +3
Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to a…
Accelerated Parallel Tempering via Neural Transports
Leo Zhang, Peter Potaptchik, Jiajun He +5
Markov Chain Monte Carlo (MCMC) algorithms are essential tools in computational statistics for sampling from unnormalised probability distributions, but can be fragile when targeti…
Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
Tyler Farghly, Patrick Rebeschini, George Deligiannidis +1
The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown…
Score-Optimal Diffusion Schedules
Christopher Williams, Andrew Campbell, Arnaud Doucet +1
Denoising diffusion models (DDMs) offer a flexible framework for sampling from high dimensional data distributions. DDMs generate a path of probability distributions interpolating…