b'Luke Metz'

research

∙ 04/21/2023

Noise-Reuse in Online Evolution Strategies

Online evolution strategies have become an attractive alternative to aut...

0 Oscar Li, et al. ∙

research

∙ 12/08/2022

General-Purpose In-Context Learning by Meta-Learning Transformers

Modern machine learning requires system designers to specify aspects of ...

0 Louis Kirsch, et al. ∙

research

∙ 12/02/2022

Transformer-Based Learned Optimization

In this paper, we propose a new approach to learned optimization. As com...

0 Erik Gärtner, et al. ∙

research

∙ 11/17/2022

VeLO: Training Versatile Learned Optimizers by Scaling Up

While deep learning models have replaced hand-designed features across m...

0 Luke Metz, et al. ∙

research

∙ 10/11/2022

Discovered Policy Optimisation

Tremendous progress has been made in reinforcement learning (RL) over th...

18 Chris Lu, et al. ∙

research

∙ 09/22/2022

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases

Learned optimizers – neural networks that are trained to act as optimize...

21 James Harrison, et al. ∙

research

∙ 03/22/2022

Practical tradeoffs between memory, compute, and performance in learned optimizers

Optimization plays a costly and crucial role in developing machine learn...

10 Luke Metz, et al. ∙

research

∙ 12/27/2021

Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies

Unrolled computation graphs arise in many scenarios, including training ...

9 Paul Vicol, et al. ∙

research

∙ 12/24/2021

Lyapunov Exponents for Diversity in Differentiable Games

Ridge Rider (RR) is an algorithm for finding diverse solutions to optimi...

12 Jonathan Lorraine, et al. ∙

research

∙ 11/10/2021

Gradients are Not All You Need

Differentiable programming techniques are widely used in the community a...

14 Luke Metz, et al. ∙

research

∙ 07/20/2021

Learn2Hop: Learned Optimization on Rough Landscapes

Optimization of non-convex loss surfaces containing many local minima re...

7 Amil Merchant, et al. ∙

research

∙ 01/14/2021

Training Learned Optimizers with Randomly Initialized Learned Optimizers

Learned optimizers are increasingly effective, with performance exceedin...

8 Luke Metz, et al. ∙

research

∙ 12/07/2020

Parallel Training of Deep Networks with Local Updates

Deep learning models trained on large data sets have been widely success...

8 Michael (Misha) Laskin, et al. ∙

research

∙ 11/12/2020

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

Over the last decade, a single algorithm has changed many facets of our ...

11 Jack Parker-Holder, et al. ∙

research

∙ 11/04/2020

Reverse engineering learned optimizers reveals known and novel mechanisms

Learned optimizers are algorithms that can themselves be trained to solv...

22 Niru Maheswaranathan, et al. ∙

research

∙ 09/23/2020

Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves

Much as replacing hand-designed features with learned functions has revo...

12 Luke Metz, et al. ∙

research

∙ 07/01/2020

On Linear Identifiability of Learned Representations

Identifiability is a desirable property of a statistical model: it impli...

3 Geoffrey Roeder, et al. ∙

research

∙ 02/27/2020

Using a thousand optimization tasks to learn hyperparameter search strategies

We present TaskSet, a dataset of tasks for use in training and evaluatin...

71 Luke Metz, et al. ∙

research

∙ 01/10/2020

Towards GAN Benchmarks Which Require Generalization

For many evaluation metrics commonly used as benchmarks for unconditiona...

0 Ishaan Gulrajani, et al. ∙

research

∙ 10/29/2019

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction

Much of model-based reinforcement learning involves learning a model of ...

30 C. Daniel Freeman, et al. ∙

research

∙ 09/20/2019

Learning an Adaptive Learning Rate Schedule

The learning rate is one of the most important hyper-parameters for mode...

10 Zhen Xu, et al. ∙

research

∙ 06/08/2019

Using learned optimizers to make models robust to input noise

State-of-the art vision models can achieve superhuman performance on ima...

0 Luke Metz, et al. ∙

research

∙ 10/24/2018

Learned optimizers that outperform SGD on wall-clock and test loss

Deep learning has shown that learned functions can dramatically outperfo...

8 Luke Metz, et al. ∙

research

∙ 10/24/2018

Learned optimizers that outperform SGD on wall-clock and validation loss

Deep learning has shown that learned functions can dramatically outperfo...

2 Luke Metz, et al. ∙

research

∙ 06/26/2018

Guided evolutionary strategies: escaping the curse of dimensionality in random search

Many applications in machine learning require optimizing a function whos...

2 Niru Maheswaranathan, et al. ∙

research

∙ 03/31/2018

Learning Unsupervised Learning Rules

A major goal of unsupervised learning is to discover data representation...

0 Luke Metz, et al. ∙

research

∙ 01/09/2018

Adversarial Spheres

State of the art computer vision models have been shown to be vulnerable...

0 Justin Gilmer, et al. ∙

research

∙ 05/14/2017

Discrete Sequential Prediction of Continuous Actions for Deep RL

It has long been assumed that high dimensional continuous control proble...

0 Luke Metz, et al. ∙

research

∙ 03/31/2017

BEGAN: Boundary Equilibrium Generative Adversarial Networks

We propose a new equilibrium enforcing method paired with a loss derived...

0 David Berthelot, et al. ∙

research

∙ 11/07/2016

Unrolled Generative Adversarial Networks

We introduce a method to stabilize Generative Adversarial Networks (GANs...

0 Luke Metz, et al. ∙

Luke Metz

Featured Co-authors