
Controlling Style and Semantics in WeaklySupervised Image Generation
We propose a weaklysupervised approach for conditional image generation...
read it

The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
We investigate conditions under which test statistics exist that can rel...
read it

Adversarial Training Generalizes Datadependent Spectral Norm Regularization
We establish a theoretical link between adversarial training and operato...
read it

Evaluating GANs via Duality
Generative Adversarial Networks (GANs) have shown great results in accur...
read it

Adversarially Robust Training through Structured Gradient Regularization
We propose a novel datadependent structured gradient regularizer to inc...
read it

A Distributed SecondOrder Algorithm You Can Trust
Due to the rapid growth of data and computational resources, distributed...
read it

Flexible Prior Distributions for Deep Generative Models
We consider the problem of training generative models with deep neural n...
read it

Semantic Interpolation in Implicit Models
In implicit models, one often interpolates between sampled points in lat...
read it

Generator Reversal
We consider the problem of training generative models with deep neural n...
read it

Cosmological model discrimination with Deep Learning
We demonstrate the potential of Deep Learning methods for measurements o...
read it

An Online Learning Approach to Generative Adversarial Networks
We consider the problem of training generative models with a Generative ...
read it

Stabilizing Training of Generative Adversarial Networks through Regularization
Deep generative models based on Generative Adversarial Networks (GANs) h...
read it

Learning Aerial Image Segmentation from Online Maps
This study deals with semantic segmentation of highresolution (aerial) ...
read it

A Semisupervised Framework for Image Captioning
Stateoftheart approaches for image captioning require supervised trai...
read it

Variance Reduced Stochastic Gradient Descent with Neighbors
Stochastic Gradient Descent (SGD) is a workhorse in machine learning, ye...
read it

Probabilistic Latent Semantic Analysis
Probabilistic Latent Semantic Analysis is a novel statistical technique ...
read it

Exponential Families for Conditional Random Fields
In this paper we de ne conditional random elds in reproducing kernel Hil...
read it

Deep Joint Entity Disambiguation with Local Neural Attention
We propose a novel deep learning model for joint documentlevel entity d...
read it

Leveraging Large Amounts of Weakly Supervised Data for MultiLanguage Sentiment Classification
This paper presents a novel approach for multilingual sentiment classif...
read it

Fully CharacterLevel Neural Machine Translation without Explicit Segmentation
Most existing machine translation systems operate at the level of words,...
read it

Probabilistic BagOfHyperlinks Model for Entity Linking
Many fundamental problems in natural language processing rely on determi...
read it

The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
BlackBox attacks on machine learning models occur when an attacker, des...
read it

Parametrizing filters of a CNN with a GAN
It is commonly agreed that the use of relevant invariances as a good sta...
read it

Fast Cosmic Web Simulations with Generative Adversarial Networks
Dark matter in the universe evolves through gravity to form a complex ne...
read it

Escaping Saddles with Stochastic Gradients
We analyze the variance of stochastic gradients along negative curvature...
read it

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
Learning graph representations via lowdimensional embeddings that prese...
read it

Local Saddle Point Optimization: A Curvature Exploitation Approach
Gradientbased optimization methods are the most popular choice for find...
read it

Hyperbolic Neural Networks
Hyperbolic spaces have recently gained momentum in the context of machin...
read it

Towards a Theoretical Understanding of Batch Normalization
Normalization techniques such as Batch Normalization have been applied v...
read it

Deep State Space Models for Unconditional Word Generation
Autoregressive feedback is considered a necessity for successful uncondi...
read it

ZeroShot Dual Machine Translation
Neural Machine Translation (NMT) systems rely on large amounts of parall...
read it

EndtoEnd Neural Entity Linking
Entity Linking (EL) is an essential task for semantic text understanding...
read it

Learning and Evaluating Sparse Interpretable Sentence Embeddings
Previous research on word embeddings has shown that sparse representatio...
read it

Cosmological Nbody simulations: a challenge for scalable generative models
Deep generative models, such as Generative Adversarial Networks (GANs) o...
read it

Autoregressive Text Generation Beyond Feedback Loops
Autoregressive state transitions, where predictions are conditioned on p...
read it

LeDeepChef: Deep Reinforcement Learning Agent for Families of TextBased Games
While Reinforcement Learning (RL) approaches lead to significant achieve...
read it

Mixing of Stochastic Accelerated Gradient Descent
We study the mixing properties for stochastic accelerated gradient desce...
read it

BERT as a Teacher: Contextual Embeddings for SequenceLevel Reward
Measuring the quality of a generated sequence against a set of reference...
read it