Search Results for author:
Found 12 papers, 8 papers with code
Ask Your Distribution Shift if Pre-Training is Right for You
In particular, we focus on two possible failure modes of models under distribution shift: poor extrapolation (e. g., they cannot generalize to a different domain) and biases in the training data (e. g., they rely on spurious features).
The Journey, Not the Destination: How Data Guides Diffusion Models
Then, we provide a method for computing these attributions efficiently.
Neural Nonnegative Matrix Factorization for Hierarchical Multilayer Topic Modeling
We introduce a new method based on nonnegative matrix factorization, Neural NMF, for detecting latent hierarchical structure in data.
Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation
In this work, we introduce the notion of a dataset interface: a framework that, given an input dataset and a user-specified shift, returns instances from that input distribution that exhibit the desired shift.
Automatic Infectious Disease Classification Analysis with Concept Discovery
Automatic infectious disease classification from images can facilitate needed medical diagnoses.
A Generalized Hierarchical Nonnegative Tensor Decomposition
Hierarchical NTF (HNTF) methods have been proposed, however these methods do not naturally generalize their matrix-based counterparts.
Analysis of Legal Documents via Non-negative Matrix Factorization Methods
The California Innocence Project (CIP), a clinical law school program aiming to free wrongfully convicted prisoners, evaluates thousands of mails containing new requests for assistance and corresponding case files.
Learning low-rank latent mesoscale structures in networks
It is common to use networks to encode the architecture of interactions between entities in complex systems in the physical, biological, social, and information sciences.
Neural Nonnegative CP Decomposition for Hierarchical Tensor Analysis
We propose a new hierarchical nonnegative CANDECOMP/PARAFAC (CP) decomposition (hierarchical NCPD) model and a training method, Neural NCPD, for performing hierarchical topic modeling on multi-modal tensor data.
Learning to predict synchronization of coupled oscillators on randomly generated graphs
However, in the problem setting where these graph statistics cannot distinguish the two classes very well (e. g., when the graphs are generated from the same random graph model), we find that pairing a few iterations of the initial dynamics along with the graph statistics as the input to our classification algorithms can lead to significant improvement in accuracy; far exceeding what is known by the classical oscillator theory.
On a Guided Nonnegative Matrix Factorization
Fully unsupervised topic models have found fantastic success in document clustering and classification.
Feature Selection on Lyme Disease Patient Survey Data
We first analyze the general performance of the model and then identify the most important features for predicting participant answers to GROC.
