Search Results for author:
Found 12 papers, 3 papers with code
Using Higher-Order Moments to Assess the Quality of GAN-generated Image Features
The rapid advancement of Generative Adversarial Networks (GANs) necessitates the need to robustly evaluate these models.
Self-Consuming Generative Models Go MAD
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models.
Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks
We study how the generalization behavior of transfer learning is affected by the dataset size in the source and target tasks, the number of transferred layers that are kept frozen in the target DNN training, and the similarity between the source and target tasks.
TITAN: Bringing The Deep Image Prior to Implicit Representations
We study the interpolation capabilities of implicit neural representations (INRs) of images.
Boomerang: Local sampling on image manifolds using diffusion models
As implied by its name, Boomerang local sampling involves adding noise to an input image, moving it closer to the latent space, and then mapping it back to the image manifold through a partial reverse diffusion process.
NFT-K: Non-Fungible Tangent Kernels
To further contribute interpretability with respect to classification and the layers, we develop a new network as a combination of multiple neural tangent kernels, one to model each layer of the deep neural network individually as opposed to past work which attempts to represent the entire network via a single neural tangent kernel.
Evaluating generative networks using Gaussian mixtures of image features
We define a performance measure, which we call WaM, on two sets of images by using Inception-v3 (or another classifier) to featurize the images, estimate two GMMs, and use the restricted $2$-Wasserstein distance to compare the GMMs.
Double Descent and Other Interpolation Phenomena in GANs
We show that overparameterization can improve generalization performance and accelerate the training process.
Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels
High dimensionality poses many challenges to the use of data, from visualization and interpretation, to prediction and storage for historical preservation.
Ensembles of Generative Adversarial Networks for Disconnected Data
They can be represented in two ways: With an ensemble of networks or with a single network with truncated latent space.
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors
We study the linear subspace fitting problem in the overparameterized setting, where the estimated subspace can perfectly interpolate the training examples.
A GOODNESS OF FIT MEASURE FOR GENERATIVE NETWORKS
We define a goodness of fit measure for generative networks which captures how well the network can generate the training data, which is necessary to learn the true data distribution.
