Before deploying machine learning models it is critical to assess their
...
Meta and transfer learning are two successful families of approaches to
...
The idea behind the unsupervised learning of disentangled
representation...
While the Transformer architecture has become the de-facto standard for
...
Transfer of pre-trained representations can improve sample efficiency an...
The goal of the unsupervised learning of disentangled representations is...
We study deep neural networks (DNNs) trained on natural image data with
...
In recent years, on-policy reinforcement learning (RL) has been successf...
We study the prediction of the accuracy of a neural network given only i...
Uncertainty quantification for deep learning is a challenging open probl...
Transfer of pre-trained representations improves sample efficiency and
s...
We propose a general framework for self-supervised learning of transfera...
Coupling the high-fidelity generation capabilities of label-conditional ...
Many recent methods for unsupervised or self-supervised representation
l...
Recent progress in the field of reinforcement learning has been accelera...
An agent learning through interactions should balance its action selecti...
We consider the core reinforcement-learning problem of on-policy value
f...
In semi-supervised classification, one is given access both to labeled a...
Despite the tremendous progress in the estimation of generative models, ...
Deep generative models are becoming a cornerstone of modern machine lear...
The softmax function on top of a final linear layer is the de facto meth...
Fine-tuning large pre-trained models is an effective transfer mechanism ...
Recent advances in deep generative models have lead to remarkable progre...
In recent years, the interest in unsupervised learning of disentangled
r...
Deep generative models seek to recover the process with which the observ...
Rewards are sparse in the real world and most today's reinforcement lear...
Training Generative Adversarial Networks (GANs) is notoriously challengi...
Generative Adversarial Networks (GANs) are a class of deep generative mo...
Temporal-Difference learning (TD) [Sutton, 1988] with function approxima...
Generative Adversarial Networks (GANs) are a promising approach to langu...
Recent advances in generative modeling have led to an increased interest...
Clustering is a cornerstone of unsupervised learning which can be though...
We propose a new learning paradigm called Deep Memory. It has the potent...
Deep neural networks are often trained in the over-parametrized regime (...
Generative adversarial networks (GAN) are a powerful subclass of generat...
We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for buil...
Generic text embeddings are successfully used in a variety of tasks. How...
We study unsupervised generative modeling in terms of the optimal transp...
Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an
e...