Gavin Taylor
11 papers · 2014–2022 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (26) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π€
Dynamic Duo
(10)
ποΈ
Keyword Collector
(52)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(9)
Learning Types Β· Machine Learning
(7)
Deep Learning
(5)
Application Areas
(5)
Artificial Intelligence
(4)
Core AI
(4)
Mathematics & Optimization
(3)
Learning Types Β· Deep Learning
(3)
Optimization
(3)
Optimization & Theory Β· Machine Learning
(3)
Computer Vision
(1)
Analysis
(1)
Architectures
(1)
Learning Paradigms
(1)
Optimization & Theory Β· Deep Learning
(1)
Keywords
adversarial attack
(5)
adversarial perturbation
(2)
clean-label attack
(2)
data poisoning
(2)
non-convex optimization
(1)
distributed optimization
(1)
robust optimization
(1)
model robustness
(1)
neural network training
(1)
data augmentation
(1)
distributed learning
(1)
adversarial training
(1)
face detection
(1)
loss landscape
(1)
markov decision process
(1)
distributed computing
(1)
l1 regularization
(1)
feature space
(1)
value function approximation
(1)
graph classification
(1)
Papers
Robust Optimization As Data Augmentation for Large-Scale Graphs
CVPR 2022
LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
ICLR 2021
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
ICLR 2021
MetaPoison: Practical General-purpose Clean-label Data Poisoning
NeurIPS 2020
Adversarial training for free!
NeurIPS 2019
Transferable Clean-Label Poisoning Attacks on Deep Neural Nets
ICML 2019
Visualizing the Loss Landscape of Neural Nets
NeurIPS 2018
Adaptive Consensus ADMM for Distributed Optimization
ICML 2017
Training Neural Networks Without Gradients: A Scalable ADMM Approach
ICML 2016
Unwrapping ADMM: Efficient Distributed Computing via Transpose Reduction
AISTATS 2016
An Analysis of State-Relevance Weights and Sampling Distributions on L1-Regularized Approximate Linear Programming Approximation Accuracy
ICML 2014