Luke Metz
15 papers · 2019–2023 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🐝 Cross-Pollinator (4) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (5)
🌍
Conference Polyglot
(5)
🌈
Renaissance Researcher
(5)
👑
Triple Crown
🏆
Keyword Champion
(2)
📈
Trend Setter
💎
Century Club
(15)
⚡
Prolific Year
(5)
🔥
Unstoppable
(5)
Conferences
NIPS (6)
ICML (5)
ICLR (2)
CVPR (1)
IJCAI (1)
Top co-authors
Keywords
neural network optimization
(4)
learned optimizer
(4)
reinforcement learning
(2)
gradient estimation
(2)
learned optimization
(2)
representation learning
(2)
stochastic gradient descent
(2)
evolution strategy
(2)
optimization algorithm
(2)
policy optimization
(1)
gradient descent
(1)
function space
(1)
model-based reinforcement learning
(1)
online optimization
(1)
non-convex optimization
(1)
hyperparameter tuning
(1)
loss landscape
(1)
learning rate adaptation
(1)
random search
(1)
independent components analysis
(1)
Papers
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies
NIPS 2023
Transformer-Based Learned Optimization
CVPR 2023
A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases
NIPS 2022
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract)
IJCAI 2022
Discovered Policy Optimisation
NIPS 2022
On Linear Identifiability of Learned Representations
ICML 2021
Learn2Hop: Learned Optimization on Rough Landscapes
ICML 2021
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
ICML 2021
Reverse engineering learned optimizers reveals known and novel mechanisms
NIPS 2021
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
NIPS 2020
Towards GAN Benchmarks Which Require Generalization
ICLR 2019
Learning to Predict Without Looking Ahead: World Models Without Forward Prediction
NIPS 2019
Meta-Learning Update Rules for Unsupervised Representation Learning
ICLR 2019
Guided evolutionary strategies: augmenting random search with surrogate gradients
ICML 2019
Understanding and correcting pathologies in the training of learned optimizers
ICML 2019