Luke Metz
15 papers · 2019–2023 · 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 ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (25) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π Triple Crown
π
Triple Crown
π
Trend Setter
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(56)
Venues
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory Β· Machine Learning
(11)
Deep Learning
(6)
Mathematics & Optimization
(4)
Reinforcement Learning
(4)
Methods
(4)
Optimization
(4)
Artificial Intelligence
(3)
Core Methods
(3)
Learning Paradigms Β· Machine Learning
(3)
Learning Paradigms Β· Artificial Intelligence
(2)
Learning Types Β· Machine Learning
(2)
Learning Types Β· Deep Learning
(2)
Optimization & Theory Β· Deep Learning
(2)
Applications
(1)
Keywords
neural network optimization
(4)
learned optimizer
(4)
gradient estimation
(2)
optimization algorithm
(2)
reinforcement learning
(2)
representation learning
(2)
learned optimization
(2)
stochastic gradient descent
(2)
evolution strategy
(2)
feature learning
(1)
loss landscape
(1)
benchmark evaluation
(1)
function space
(1)
gradient descent
(1)
semi-supervised classification
(1)
independent component analysis
(1)
independent components analysis
(1)
variance reduction
(1)
policy optimization
(1)
online optimization
(1)
Papers
Transformer-Based Learned Optimization
CVPR 2023
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
NeurIPS 2023
A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
NeurIPS 2022
Discovered Policy Optimisation
NeurIPS 2022
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract)
IJCAI 2022
Learn2Hop: Learned Optimization on Rough Landscapes
ICML 2021
On Linear Identifiability of Learned Representations
ICML 2021
Reverse engineering learned optimizers reveals known and novel mechanisms
NeurIPS 2021
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
ICML 2021
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
NeurIPS 2020
Guided evolutionary strategies: augmenting random search with surrogate gradients
ICML 2019
Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
NeurIPS 2019
Meta-Learning Update Rules for Unsupervised Representation Learning
ICLR 2019
Towards GAN Benchmarks Which Require Generalization
ICLR 2019
Understanding and correcting pathologies in the training of learned optimizers
ICML 2019