Search Results for author:
Found 8 papers, 5 papers with code
Generalization in diffusion models arises from geometry-adaptive harmonic representations
Finally, we show that when trained on regular image classes for which the optimal basis is known to be geometry-adaptive and harmonic, the denoising performance of the networks is near-optimal.
Conditionally Strongly Log-Concave Generative Models
There is a growing gap between the impressive results of deep image generative models and classical algorithms that offer theoretical guarantees.
A Rainbow in Deep Network Black Boxes
Gaussian rainbow networks are defined with Gaussian weight distributions.
Learning multi-scale local conditional probability models of images
We instantiate this model using convolutional neural networks (CNNs) with local receptive fields, which enforce both the stationarity and Markov properties.
Wavelet Score-Based Generative Modeling
This is because of ill-conditioning properties of the score that we analyze mathematically.
Phase Collapse in Neural Networks
Spatial variability is therefore transformed into variability along channels.
Tight Frame Contractions in Deep Networks
Numerical experiments demonstrate that deep neural networks classifiers progressively separate class distributions around their mean, achieving linear separability.
Separation and Concentration in Deep Networks
On the opposite, a soft-thresholding on tight frames can reduce within-class variabilities while preserving class means.
