Search Results for author:
Found 9 papers, 5 papers with code
Self-Improving Diffusion Models with Synthetic Data
Unfortunately, training new generative models with synthetic data from current or past generation models creates an autophagous (self-consuming) loop that degrades the quality and/or diversity of the synthetic data in what has been termed model autophagy disorder (MAD) and model collapse.
Ranked #1 on
Image Generation
on ImageNet 64x64
An Adaptive Tangent Feature Perspective of Neural Networks
In order to better understand feature learning in neural networks, we propose a framework for understanding linear models in tangent feature space where the features are allowed to be transformed during training.
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.
TITAN: Bringing The Deep Image Prior to Implicit Representations
We study the interpolation capabilities of implicit neural representations (INRs) of images.
NeuroView-RNN: It's About Time
A key interpretability issue with RNNs is that it is not clear how each hidden state per time step contributes to the decision-making process in a quantitative manner.
Covariate Balancing Methods for Randomized Controlled Trials Are Not Adversarially Robust
Covariate balancing methods increase the similarity between the distributions of the two groups' covariates.
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.
Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data
Kernels derived from deep neural networks (DNNs) in the infinite-width regime provide not only high performance in a range of machine learning tasks but also new theoretical insights into DNN training dynamics and generalization.
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.
