5.7k citations · 17.6k across the 75 of their papers we have counts for
35 papers · 1 filter
Teaching Algorithmic Reasoning via In-context Learning
Hattie Zhou, Azade Nova, Hugo Larochelle +3
Large language models (LLMs) have shown increasing in-context learning capabilities through scaling up model and data size. Despite this progress, LLMs are still unable to solve al…
Repository-Level Prompt Generation for Large Language Models of Code
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
With the success of large language models (LLMs) of code and their use as code assistants (e.g. Codex used in GitHub Copilot), techniques for introducing domain-specific knowledge…
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
David Bieber, Rishab Goel, Daniel Zheng +2
The execution behavior of a program often depends on external resources, such as program inputs or file contents, and so cannot be run in isolation. Nevertheless, software develope…
Fortuitous Forgetting in Connectionist Networks
Hattie Zhou, Ankit Vani, Hugo Larochelle +1
Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "f…
Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning
Utku Evci, Vincent Dumoulin, Hugo Larochelle +1
Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing…
Learning a Universal Template for Few-shot Dataset Generalization
Eleni Triantafillou, Hugo Larochelle, Richard Zemel +1
Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purp…
Learning to Combine Per-Example Solutions for Neural Program Synthesis
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
The goal of program synthesis from examples is to find a computer program that is consistent with a given set of input-output examples. Most learning-based approaches try to find a…
Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
Vincent Dumoulin, Neil Houlsby, Utku Evci +4
Meta and transfer learning are two successful families of approaches to few-shot learning. Despite highly related goals, state-of-the-art advances in each family are measured large…
Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks
David Bieber, Charles Sutton, Hugo Larochelle +1
Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks including code completion, bug finding, and program repair. They benefit from l…
Revisiting Fundamentals of Experience Replay
William Fedus, Prajit Ramachandran, Rishabh Agarwal +4
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic…
Learning Graph Structure With A Finite-State Automaton Layer
Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow
Graph-based neural network models are producing strong results in a number of domains, in part because graphs provide flexibility to encode domain knowledge in the form of relation…
A Universal Representation Transformer Layer for Few-Shot Image Classification
Lu Liu, William Hamilton, Guodong Long +2
Few-shot classification aims to recognize unseen classes when presented with only a small number of samples. We consider the problem of multi-domain few-shot image classification,…
Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
Joelle Pineau, Philippe Vincent-Lamarre, Koustuv Sinha +5
One of the challenges in machine learning research is to ensure that presented and published results are sound and reliable. Reproducibility, that is obtaining similar results as p…
On-the-Fly Adaptation of Source Code Models using Meta-Learning
Disha Shrivastava, Hugo Larochelle, Daniel Tarlow
The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome. One of the most popular approaches for the adaptation…
Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling
Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein +4
We show that the sum of the implicit generator log-density of a GAN with the logit score of the discriminator defines an energy function which yields the true data densi…
Diversity inducing Information Bottleneck in Model Ensembles
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal +3
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive…
Curriculum By Smoothing
Samarth Sinha, Animesh Garg, Hugo Larochelle
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in…
On Catastrophic Interference in Atari 2600 Games
William Fedus, Dibya Ghosh, John D. Martin +3
Model-free deep reinforcement learning is sample inefficient. One hypothesis -- speculated, but not confirmed -- is that catastrophic interference within an environment inhibits le…
A RAD approach to deep mixture models
Laurent Dinh, Jascha Sohl-Dickstein, Hugo Larochelle +1
Flow based models such as Real NVP are an extremely powerful approach to density estimation. However, existing flow based models are restricted to transforming continuous densities…
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin +8
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and d…
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
Gabriel Huang, Hugo Larochelle, Simon Lacoste-Julien
We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduc…
The Hanabi Challenge: A New Frontier for AI Research
Nolan Bard, Jakob N. Foerster, Sarath Chandar +12
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made…
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Anirudh Goyal, Philemon Brakel, William Fedus +5
In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provide a relevant learning signal. Hence, we…
Meta-Learning for Semi-Supervised Few-Shot Classification
Mengye Ren, Eleni Triantafillou, Sachin Ravi +5
In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has…