activity
20182021
collaborators

9 papers

stat.ML2021

Online Feature Screening for Data Streams with Concept Drift

Mingyuan Wang, Adrian Barbu

Screening feature selection methods are often used as a preprocessing step for reducing the number of variables before training step. Traditional screening methods only focus on de…

cs.LG2020

A study of local optima for learning feature interactions using neural networks

Yangzi Guo, Adrian Barbu

In many fields such as bioinformatics, high energy physics, power distribution, etc., it is desirable to learn non-linear models where a small number of variables are selected and…

cs.LG2020

Neural Rule Ensembles: Encoding Sparse Feature Interactions into Neural Networks

Gitesh Dawer, Yangzi Guo, Sida Liu +1

Artificial Neural Networks form the basis of very powerful learning methods. It has been observed that a naive application of fully connected neural networks to data with many irre…

cs.LG2020

Network Pruning via Annealing and Direct Sparsity Control

Yangzi Guo, Yiyuan She, Adrian Barbu

Artificial neural networks (ANNs) especially deep convolutional networks are very popular these days and have been proved to successfully offer quite reliable solutions to many vis…

cs.AI2019

Playing Atari Ball Games with Hierarchical Reinforcement Learning

Hua Huang, Adrian Barbu

Human beings are particularly good at reasoning and inference from just a few examples. When facing new tasks, humans will leverage knowledge and skills learned before, and quickly…

cs.LG2019

The Generalization-Stability Tradeoff In Neural Network Pruning

Brian R. Bartoldson, Ari S. Morcos, Adrian Barbu +1

Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is partic…