Gavin Taylor

发表

An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning

Lihong Li, Michael L. Littman, Gavin Taylor, 2008, ICML '08.

A Novel Benchmark Methodology and Data Repository for Real-life Reinforcement Learning

Ronald E. Parr, M. Littman, Lihong Li, 2009 .

Training Neural Networks Without Gradients: A Scalable ADMM Approach

Zheng Xu, Tom Goldstein, Bharat Singh, 2016, ICML.

Kernelized value function approximation for reinforcement learning

Gavin Taylor, Ronald Parr, Ronald E. Parr, 2009, ICML '09.

Unwrapping ADMM: Efficient Distributed Computing via Transpose Reduction

Tom Goldstein, Gavin Taylor, Kent Sayre, 2015, AISTATS.

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition pdf

Micah Goldblum, Tom Goldstein, Gavin Taylor, 2021, ICLR.

An Application of Reinforcement Learning to Supervised Autonomy

Gavin Taylor, Kawika Barabin, K. Sayre, 2015 .

Blackbox Clean-Label Poisoning Attacks on Neural Networks

Chen Zhu, Tom Goldstein, Christoph Studer, 2019, ICML 2019.

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

Gavin Taylor, T. Goldstein, Liam Fowl, 2020, ICLR.

Scalable Classifiers with ADMM and Transpose Reduction

Zheng Xu, Tom Goldstein, Gavin Taylor, 2017, AAAI Workshops.

FLAG: Adversarial Data Augmentation for Graph Neural Networks pdf

Bernard Ghanem, Tom Goldstein, Gavin Taylor, 2020, ArXiv.

Reports of the 2013 AAAI Spring Symposium Series

Erez Karpas, Francesca Rossi, Takashi Kido, 2013, AI Mag..

Layer-Specific Adaptive Learning Rates for Deep Networks

Bharat Singh, Thomas Goldstein, Gavin Taylor, 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

Adversarial Training for Free!

Larry S. Davis, Zheng Xu, Tom Goldstein, 2019, NeurIPS.

Visualizing the Loss Landscape of Neural Nets

Hao Li, Tom Goldstein, Gavin Taylor, 2017, NeurIPS.

Robust Optimization as Data Augmentation for Large-scale Graphs

Gavin Taylor, T. Goldstein, Bernard Ghanem, 2020, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

FLAG: Adversarial Data Augmentation for Graph Neural Networks pdf

Bernard Ghanem, Tom Goldstein, Gavin Taylor, 2020, ArXiv.

Introduction to the Symposium on AI and the Mitigation of Human Error

Donald A. Sofge, Gavin Taylor, Ranjeev Mittu, 2016, AAAI Spring Symposia.

Execute Order 66: Targeted Data Poisoning for Reinforcement Learning

Gavin Taylor, T. Goldstein, Liam Fowl, 2022, ArXiv.

MetaPoison: Practical General-purpose Clean-label Data Poisoning pdf

Jonas Geiping, Liam Fowl, Tom Goldstein, 2020, NeurIPS.

Transferable Clean-Label Poisoning Attacks on Deep Neural Nets pdf

Tom Goldstein, Christoph Studer, Ali Shafahi, 2019, ICML.

Adaptive Consensus ADMM for Distributed Optimization pdf

Zheng Xu, Xiaoming Yuan, Tom Goldstein, 2017, ICML.

Value Function Approximation in Noisy Environments Using Locally Smoothed Regularized Approximate Linear Programs pdf

Gavin Taylor, Ronald Parr, Ronald E. Parr, 2012, UAI.

Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes

Marek Petrik, Shlomo Zilberstein, Gavin Taylor, 2010, ICML.

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting

Frank Alexander Kraemer, Abdulmajid Murad, Gavin Taylor, 2021, Sensors.

The National Airworthiness Council artificial intelligence working group (NACAIWG) summit proceedings 2022

Donald H. Costello, Gavin Taylor, Jonathon Parry, 2023, Syst. Eng..

Feature Selection for Value Function Approximation

Gavin Taylor, Gavin Taylor, 2011 .