2 citations · 2 across the 6 of their papers we have counts for
5 papers · 1 filter
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
Naïl B. Khelifa, Richard E. Turner, Ramji Venkataramanan
Score-based diffusion models are typically trained by minimizing the score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discr…
Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization
Naïl B. Khelifa, Richard E. Turner, Ramji Venkataramanan
Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound…
Fearless Stochasticity in Expectation Propagation
Jonathan So, Richard E. Turner
Expectation propagation (EP) is a family of algorithms for performing approximate inference in probabilistic models. The updates of EP involve the evaluation of moments -- expectat…
Identifiable Feature Learning for Spatial Data with Nonlinear ICA
Hermanni Hälvä, Jonathan So, Richard E. Turner +1
Recently, nonlinear ICA has surfaced as a popular alternative to the many heuristic models used in deep representation learning and disentanglement. An advantage of nonlinear ICA i…
Optimising Distributions with Natural Gradient Surrogates
Jonathan So, Richard E. Turner
Natural gradient methods have been used to optimise the parameters of probability distributions in a variety of settings, often resulting in fast-converging procedures. Unfortunate…