
No MCMC for me: Amortized sampling for fast and stable training of energybased models
EnergyBased Models (EBMs) present a flexible and appealing way to repre...
read it

Learned Hardware/Software CoDesign of Neural Accelerators
The use of deep learning has grown at an exponential rate, giving rise t...
read it

Optimizing Longterm Social Welfare in Recommender Systems: A Constrained Matching Approach
Most recommender systems (RS) research assumes that a user's utility can...
read it

An Imitation Learning Approach for Cache Replacement
Program execution speed critically depends on increasing cache hits, as ...
read it

Big SelfSupervised Models are Strong SemiSupervised Learners
One paradigm for learning from few labeled examples while making best us...
read it

Neural Execution Engines: Learning to Execute Subroutines
A significant effort has been made to train neural networks that replica...
read it

SentenceMIM: A Latent Variable Language Model
We introduce sentenceMIM, a probabilistic autoencoder for language mode...
read it

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
We propose to reinterpret a standard discriminative classifier of p(yx)...
read it

MIM: Mutual Information Machine
We introduce the Mutual Information Machine (MIM), an autoencoder model ...
read it

High Mutual Information in Representation Learning with Symmetric Variational Inference
We introduce the Mutual Information Machine (MIM), a novel formulation o...
read it

Learning Execution through Neural Code Fusion
As the performance of computer systems stagnates due to the end of Moore...
read it

Flexibly Fair Representation Learning by Disentanglement
We consider the problem of learning representations that achieve group a...
read it

Learning Sparse Networks Using Targeted Dropout
Neural networks are easier to optimise when they have many more weights ...
read it

Graph Normalizing Flows
We introduce graph normalizing flows: a new, reversible graph neural net...
read it

Neural Networks for Modeling Source Code Edits
Programming languages are emerging as a challenging and interesting doma...
read it

MetaDataset: A Dataset of Datasets for Learning to Learn from Few Examples
Fewshot classification refers to learning a classifier for new classes ...
read it

Learning Memory Access Patterns
The explosion in workload complexity and the recent slowdown in Moore's...
read it

MetaLearning for SemiSupervised FewShot Classification
In fewshot classification, we are interested in learning algorithms tha...
read it

An online sequencetosequence model for noisy speech recognition
Generative models have long been the dominant approach for speech recogn...
read it

Learning Hard Alignments with Variational Inference
There has recently been significant interest in hard attention models fo...
read it

Prototypical Networks for Fewshot Learning
We propose prototypical networks for the problem of fewshot classificat...
read it

The Variational Fair Autoencoder
We investigate the problem of learning representations that are invarian...
read it

Predicting Deep ZeroShot Convolutional Neural Networks using Textual Descriptions
One of the main challenges in ZeroShot Learning of visual categories is...
read it

Scalable Bayesian Optimization Using Deep Neural Networks
Bayesian optimization is an effective methodology for the global optimiz...
read it

Generative Moment Matching Networks
We consider the problem of learning deep generative models from data. We...
read it

Learning unbiased features
A key element in transfer learning is representation learning; if repres...
read it

Input Warping for Bayesian Optimization of Nonstationary Functions
Bayesian optimization has proven to be a highly effective methodology fo...
read it

Fast Exact Inference for Recursive Cardinality Models
Cardinality potentials are a generally useful class of high order potent...
read it

Estimating the Hessian by Backpropagating Curvature
In this work we develop Curvature Propagation (CP), a general technique ...
read it