research
∙
07/20/2023
LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Large language models (LLMs) have exhibited impressive capabilities in c...
share
research
∙
06/03/2021
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
Recent work [Papyan, Han, and Donoho, 2020] discovered a phenomenon call...
research
∙
08/27/2020
Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra
Numerous researchers recently applied empirical spectral analysis to the...
research
∙
08/18/2020
Prevalence of Neural Collapse during the terminal phase of deep learning training
Modern practice for training classification deepnets involves a Terminal...
research
∙
06/10/2019
Degrees of Freedom Analysis of Unrolled Neural Networks
Unrolled neural networks emerged recently as an effective model for lear...
research
∙
01/24/2019
Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians
We consider deep classifying neural networks. We expose a structure in t...
research
∙
11/16/2018
The Full Spectrum of Deep Net Hessians At Scale: Dynamics with Sample Size
Previous works observed the spectrum of the Hessian of the training loss...
research
∙
06/01/2018
Neural Proximal Gradient Descent for Compressive Imaging
Recovering high-resolution images from limited sensory data typically le...
research
∙
11/27/2017
Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery
Recovering images from undersampled linear measurements typically leads ...
research
∙
08/29/2017
Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
The recently proposed Multi-Layer Convolutional Sparse Coding (ML-CSC) m...
research
∙
05/09/2017
Convolutional Dictionary Learning via Local Processing
Convolutional Sparse Coding (CSC) is an increasingly popular model in th...
research
∙
11/25/2016
Multimodal Latent Variable Analysis
Consider a set of multiple, multimodal sensors capturing a complex syste...
research
∙
07/27/2016