
Depth Without the Magic: Inductive Bias of Natural Gradient Descent
In gradient descent, changing how we parametrize the model can lead to d...
read it

Algorithmic Amplification of Politics on Twitter
Content on Twitter's home timeline is selected and ordered by personaliz...
read it

Efficient Wasserstein Natural Gradients for Reinforcement Learning
A novel optimization approach is proposed for application to policy grad...
read it

Deep Bayesian Bandits: Exploring in Online Personalized Recommendations
Recommender systems trained in a continuous learning fashion are plagued...
read it

Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems
Deep Neural Networks (DNNs) with sparse input features have been widely ...
read it

Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
One of the challenges in display advertising is that the distribution of...
read it

Adaptive PairedComparison Method for Subjective Video Quality Assessment on Mobile Devices
To effectively evaluate subjective visual quality in weaklycontrolled e...
read it

A Generative Deep Recurrent Model for Exchangeable Data
We present a novel model architecture which leverages deep learning tool...
read it

Faster gaze prediction with dense networks and Fisher pruning
Predicting human fixations from images has recently seen large improveme...
read it

On Quadratic Penalties in Elastic Weight Consolidation
Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel a...
read it

Lossy Image Compression with Compressive Autoencoders
We propose a new approach to the problem of optimizing autoencoders for ...
read it

Variational Inference using Implicit Distributions
Generative adversarial networks (GANs) have given us a great tool to fit...
read it

Amortised MAP Inference for Image Superresolution
Image superresolution (SR) is an underdetermined inverse problem, where...
read it

Is the deconvolution layer the same as a convolutional layer?
In this note, we want to focus on aspects related to two questions most ...
read it

RealTime Single Image and Video SuperResolution Using an Efficient SubPixel Convolutional Neural Network
Recently, several models based on deep neural networks have achieved gre...
read it

PhotoRealistic Single Image SuperResolution Using a Generative Adversarial Network
Despite the breakthroughs in accuracy and speed of single image superre...
read it

How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
Modern applications and progress in deep learning research have created ...
read it

OptimallyWeighted Herding is Bayesian Quadrature
Herding and kernel herding are deterministic methods of choosing samples...
read it

Bayesian Active Learning for Classification and Preference Learning
Information theoretic active learning has been widely studied for probab...
read it

A Kernel Approach to Tractable Bayesian Nonparametrics
Inference in popular nonparametric Bayesian models typically relies on s...
read it