My Selected papers from NIPS 2018 (Neurips'18)




Sunday, December 30, 2018

I attended NIPS’18 in Montreal and here is the list of papers that I found interesting from the talks and poster sessions:

Generatives And Adverserial:

GILBO: One Metric to Measure Them All

On GANs and GMMs

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

Assessing Generative Models via Precision and Recall

With Friends Like These, Who Needs Adversaries?

Generalizing to Unseen Domains via Adversarial Data Augmentation

Multimodal Generative Models for Scalable Weakly-Supervised Learning

SGD and optimization

cpSGD: Communication-efficient and differentially-private distributed SGD

How Does Batch Normalization Help Optimization?

Visualizing the Loss Landscape of Neural Nets

The Lingering of Gradients: How to Reuse Gradients Over Time

Uniform Convergence of Gradients for Non-Convex Learning and Optimization

Adaptive Methods for Nonconvex Optimization

Distributed Stochastic Optimization via Adaptive SGD

Speech

Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices

Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces

Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Language Modeling

Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models

GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking

Others:

A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers

On the Dimensionality of Word Embedding

Gaussian Process Prior Variational Autoencoders

Hierarchical Graph Representation Learning with Differentiable Pooling

Sanity Checks for Saliency Maps

Minimax Statistical Learning with Wasserstein distances

The Global Anchor Method for Quantifying Linguistic Shifts and Domain Adaptation

Blockwise Parallel Decoding for Deep Autoregressive Models

Improving Simple Models with Confidence Profiles

 

Favorite Quotes

"I have never thought of writing for reputation and honor. What I have in my heart must out; that is the reason why I compose." --Beethoven

"All models are wrong, but some are useful." --George Box

Copyright © 2015 • [Deprecated] visit: firooz.us/blog