Research and Publications
Overview
I am interested in a wide variety of topics in machine learning, including reinforcement learning and the behaviors of neural networks.
I am a co-director of the USNA's Center for High Performance Computing Education and Research.
Curriculum Vitae
Conference and Journal Papers
-
Robust Optimization as Data Augmentation for Large-scale Graphs
Kong, Li, Ding, Wu, Zhu, Ghanem, Taylor, Goldstein.
CVPR, 2022. [ pdf ] -
Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
Murad, Kraemer, Bach, Taylor.
Sensors, 2021. [ pdf ] -
Classifying Tropical Cyclone Intensity Change by Applying Machine Learning Techniques to USAF WC-130J "Hurricane Hunter" Aircraft Data and Radar Imagery
Lozano*, Herron*, Sanabia, Taylor, Ruth.
AMS, 2021. -
LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
Cherepanova, Goldblum, Foley*, Duan, Dickerson, Taylor, and Goldstein.
ICLR, 2021. [ pdf ] -
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
Geiping, Fowl, Huang, Czaja, Taylor, Moeller, and Goldstein.
ICLR, 2021. [ pdf ] -
Information-Driven Adaptive Sensing Based on Deep Reinforcement Learning
Abdulmajid Murad, Frank Kraemer, Kerstin Bach, Gavin Taylor
Internet of Things, 2020. [ pdf ] -
MetaPoison: Practical General-Purpose Clean-Label Data Poisoning
W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, Tom Goldstein.
NeurIPS, 2020. [ pdf ][ code ] -
Adversarial Training for Free!
Shafahi, Najibi, Ghiasi, Xu, Dickerson, Studer, Davis, Taylor, Goldstein.
NeurIPS 2019. [ pdf ] -
Transferable Clean-Label Poison Attacks on Convolutional Nets.
Chen Zhu, W. Ronny Huang, Hengduo Li, Gavin Taylor, Christoph Studer, Tom Goldstein.
ICML 2019. [ pdf ] -
Autonomous Management of Energy-Harvesting IoT Nodes Using Deep Reinforcement Learning.
Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach, Gavin Taylor.
SASO 2019. [ pdf ] -
Visualizing the Loss Landscape of Neural Nets.
Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Thomas Goldstein.
NeurIPS 2018. [ pdf ][ code ] -
Adaptive Consensus ADMM for Distributed Optimization.
Zheng Xu, Gavin Taylor, Hao Li, Mario A. T. Figueiredo, Xiaoming Yuan, Thomas Goldstein.
ICML 2017. [ pdf ] -
Training Neural Nets Without Gradients: A Scalable ADMM Approach.
Gavin Taylor, Ryan Burmeister*, Zheng Xu, Bharat Singh, Ankit Patel, Thomas Goldstein.
ICML 2016. [ pdf ] [ code ] -
Unwrapping ADMM: Efficient Distributed Computing via Transpose
Reduction.
Thomas Goldstein, Gavin Taylor, Kawika Barabin*, and Kent Sayre*.
AISTATS 2016. [ pdf ] -
Layer-Specific Adaptive Learning Rates for Deep Networks.
Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, and Gavin Taylor.
ICMLA 2015. [ pdf ] -
An Application of Reinforcement Learning to Supervised Autonomy.
Gavin Taylor, Kawika Barabin*, and Kent Sayre*.
ICCRTS 2015. [ pdf ] -
An Analysis of State-Relevance Weights and Sampling Distributions on
L1-Regularized Approximate Linear Programming Approximation Accuracy.
Gavin Taylor, Connor Geer*, and David Piekut*.
ICML 2014 / JMLR: W&CP 32. [ pdf ] [ Tech Report ] -
Value Function Approximation in Noisy Environments Using Locally Smoothed
Regularized Approximate Linear Programs.
Gavin Taylor and Ronald Parr.
UAI 2012. [ pdf ] -
Feature Selection Using Regularization in Approximate Linear Programs for
Markov Decision Processes.
Marek Petrik, Gavin Taylor, Ronald Parr, and Shlomo Zilberstein.
ICML 2010. [ pdf ] [ Tech Report ] -
Kernelized Value Function Approximation for Reinforcement Learning.
Gavin Taylor and Ronald Parr.
ICML 2009. [ pdf ] -
An Analysis of Linear Models, Linear Value-Function Approximation, and
Feature Selection for Reinforcement Learning.
Ronald Parr, Lihong Li, Gavin Taylor, Christopher Painter-Wakefield, and Michael Littman.
ICML 2008. [ pdf ] [ Addendum ]
* Midshipman co-author
Workshop Papers
-
Execute Order 66: Targeted Data Poisoning for Reinforcement Learning via Miniscule Perturbations.
Harrison Foley*, Liam Fowl, Tom Goldstein, and Gavin Taylor.
Workshop on Safe and Robust Control of Uncertain Systems at the 35th Conference on Neural Information Processing Systems 2022. [ pdf ] -
Scalable Classifiers with ADMM and Transpose Reduction.
Gavin Taylor, Zheng Xu, and Thomas Goldstein.
AAAI Workshop on Distributed Machine Learning, 2017. -
Neural Net Weight Initialization via Kernel Approximation.
Ryan Burmeister*, Gavin Taylor, Tom Goldstein.
NIPS Workshop on Making Sense of Big Neural Data, 2015. -
Distributed Machine Learning via Transpose Reduction.
Tom Goldstein, Gavin Taylor, Kawika Barabin*, and Kent Sayre*.
NIPS Workshop on Making Sense of Big Neural Data, 2015. -
Towards Modeling the Behavior of Autonomous Systems and Humans for Trusted
Operations.
Weiqing Gu, Ranjeev Mittu, Julie Marble, Gavin Taylor, Ciara Sibley, Joseph Coyne, and W.F. Lawless.
AAAI Symposium on the Intersection of Robust Intelligence and Trust in Autonomous Systems 2014. [ pdf ] -
An Intensive Introductory Robotics Course Without Prerequisites.
Julian Mason and Gavin Taylor.
AAAI Robotics Workshop and Exhibition 2010. [ pdf ]
Dissertation
- Feature Selection for Value Function Approximation. [ pdf ]