NeurIPS 2017

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

NeurIPS 2017 tensorflow/models

Learning in models with discrete latent variables is challenging due to high variance gradient estimators.

Filtering Variational Objectives

NeurIPS 2017 tensorflow/models

When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results.

Attention Is All You Need

NeurIPS 2017 tensorflow/models

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration.

CONSTITUENCY PARSING MACHINE TRANSLATION

LightGBM: A Highly Efficient Gradient Boosting Decision Tree

NeurIPS 2017 Microsoft/LightGBM

We prove that, since the data instances with larger gradients play a more important role in the computation of information gain, GOSS can obtain quite accurate estimation of the information gain with a much smaller data size.

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

NeurIPS 2017 jantic/DeOldify

Generative Adversarial Networks (GANs) excel at creating realistic images with complex models for which maximum likelihood is infeasible.

IMAGE GENERATION

A Unified Approach to Interpreting Model Predictions

NeurIPS 2017 slundberg/shap

Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications.

FEATURE IMPORTANCE INTERPRETABLE MACHINE LEARNING

Improved Training of Wasserstein GANs

NeurIPS 2017 eriklindernoren/Keras-GAN

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability.

CONDITIONAL IMAGE GENERATION

Convolutional Gaussian Processes

NeurIPS 2017 pyro-ppl/pyro

We present a practical way of introducing convolutional structure into Gaussian processes, making them more suited to high-dimensional inputs like images.

GAUSSIAN PROCESSES

Doubly Stochastic Variational Inference for Deep Gaussian Processes

NeurIPS 2017 pyro-ppl/pyro

Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice.

GAUSSIAN PROCESSES

Unsupervised Image-to-Image Translation Networks

NeurIPS 2017 eriklindernoren/PyTorch-GAN

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains.

DOMAIN ADAPTATION MULTIMODAL UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION UNSUPERVISED IMAGE-TO-IMAGE TRANSLATION