In the federated setup one performs an aggregation of separate local mod...
Adversarial attacks represent a security threat to machine learning base...
State-of-the-art deep neural networks have proven to be highly powerful ...
The information-theoretic framework promises to explain the predictive p...
Diffusion models (DMs) have recently emerged as a promising method in im...
Learning the tail behavior of a distribution is a notoriously difficult
...
Stochastic neural networks (SNNs) are random functions and predictions a...
In the past few years, it has been shown that deep learning systems are
...
Normalizing flows, which learn a distribution by transforming the data t...
Quantification of uncertainty is one of the most promising approaches to...
Quantification of uncertainty is one of the most promising approaches to...
Uncertainty quantification in neural networks gained a lot of attention ...
Many popular variants of graph neural networks (GNNs) that are capable o...
Monte Carlo (MC) dropout is one of the state-of-the-art approaches for
u...
The Metropolis algorithm is arguably the most fundamental Markov chain M...
Machine learning systems and also, specifically, automatic speech recogn...
In recent years generative adversarial network (GAN) based models have b...
The graphical lasso is the most popular estimator in Gaussian graphical
...
Deep neural networks can generate images that are astonishingly realisti...
Entity linking - connecting entity mentions in a natural language uttera...
Question answering has emerged as an intuitive way of querying structure...
Despite the huge success of deep neural networks (NNs), finding good
mec...
Translating natural language to SQL queries for table-based question
ans...
In this paper, we conduct an empirical investigation of neural query gra...
Building systems that can communicate with humans is a core problem in
A...
Recent work has identified that using a high learning rate or a small ba...
Knowledge graphs, on top of entities and their relationships, contain an...
We study the properties of the endpoint of stochastic gradient descent (...
Since their invention, generative adversarial networks (GANs) have becom...
We examine the role of memorization in deep learning, drawing connection...
We show that Langevin MCMC inference in an energy-based model with laten...
Estimating the log-likelihood gradient with respect to the parameters of...
We introduce a weight update formula that is expressed only in terms of
...
Efficient unsupervised training and inference in deep generative models
...
Back-propagation has been the workhorse of recent successes of deep lear...