3 papers
cs.LG2023
On Tail Decay Rate Estimation of Loss Function Distributions
Etrit Haxholli, Marco Lorenzi
The study of loss function distributions is critical to characterize a model's behaviour on a given machine learning problem. For example, while the quality of a model is commonly…
cs.LG2023
Enhanced Distribution Modelling via Augmented Architectures For Neural ODE Flows
Etrit Haxholli, Marco Lorenzi
While the neural ODE formulation of normalizing flows such as in FFJORD enables us to calculate the determinants of free form Jacobians in O(D) time, the flexibility of the transfo…
cs.LG2023
Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching
Etrit Haxholli, Marco Lorenzi
In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates extended training periods and may potenti…