Search Results for author:
Found 19 papers, 12 papers with code
DiPaCo: Distributed Path Composition
Progress in machine learning (ML) has been fueled by scaling neural network models.
Asynchronous Local-SGD Training for Language Modeling
Local stochastic gradient descent (Local-SGD), also referred to as federated averaging, is an approach to distributed optimization where each device performs more than one SGD update per communication.
DiLoCo: Distributed Low-Communication Training of Language Models
In this work, we propose a distributed optimization algorithm, Distributed Low-Communication (DiLoCo), that enables training of language models on islands of devices that are poorly connected.
NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks.
Hindering Adversarial Attacks with Implicit Neural Representations
We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-$10$ classifiers for perturbations up to $\epsilon = 8/255$ in $L_\infty$ norm and $\epsilon = 0. 5$ in $L_2$ norm.
Probing Transfer in Deep Reinforcement Learning without Task Engineering
By formally organising these modifications into several factors of variation, we are able to show that Analyses of Variance (ANOVA) are a potent tool for studying the effects of human-relevant domain changes on the learning and transfer performance of a deep reinforcement learning agent.
Prospective Learning: Principled Extrapolation to the Future
We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning.
Continual Unsupervised Representation Learning
Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially.
Meta-Learning with Warped Gradient Descent
On the other hand, approaches that try to control a gradient-based update rule typically resort to computing gradients through the learning process to obtain their meta-gradients, leading to methods that can not scale beyond few-shot task adaptation.
Task Agnostic Continual Learning via Meta Learning
One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks.
Meta-Learning with Latent Embedding Optimization
We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space.
Meta-Learning by the Baldwin Effect
The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement learning (RL).
PathNet: Evolution Channels Gradient Descent in Super Neural Networks
It is a neural network algorithm that uses agents embedded in the neural network whose task is to discover which parts of the network to re-use for new tasks.
Ranked #5 on
Continual Learning
on F-CelebA (10 tasks)
Overcoming catastrophic forgetting in neural networks
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
Ranked #3 on
Continual Learning
on F-CelebA (10 tasks)
Sim-to-Real Robot Learning from Pixels with Progressive Nets
The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills.
Progressive Neural Networks
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.
Policy Distillation
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance.
Human level control through deep reinforcement learning
We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.
