Skip to search formSkip to main contentSkip to account menu

Improved Training of Wasserstein GANs

This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.
View PDF on arXiv (opens in a new tab)

Invariant Risk Minimization

This work introduces Invariant Risk Minimization, a learning paradigm to estimate invariant correlations across multiple training distributions and shows how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.
View PDF on arXiv (opens in a new tab)

In Search of Lost Domain Generalization

This paper implements DomainBed, a testbed for domain generalization including seven multi-domain datasets, nine baseline algorithms, and three model selection criteria, and finds that, when carefully implemented, empirical risk minimization shows state-of-the-art performance across all datasets.
View PDF on arXiv (opens in a new tab)

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

The dynamic memory network (DMN), a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers, is introduced.
View PDF on arXiv (opens in a new tab)

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

It is shown that the model, which profits from combining memory-less modules, namely autoregressive multilayer perceptrons, and stateful recurrent neural networks in a hierarchical structure is able to capture underlying sources of variations in the temporal sequences over very long time spans, on three datasets of different nature.
View PDF on arXiv (opens in a new tab)

PixelVAE: A Latent Variable Model for Natural Images

Natural image modeling is a landmark challenge of unsupervised learning. Variational Autoencoders (VAEs) learn a useful latent representation and model global structure well but have difficulty…
View PDF on arXiv (opens in a new tab)

GANSynth: Adversarial Neural Audio Synthesis

Through extensive empirical investigations on the NSynth dataset, it is demonstrated that GANs are able to outperform strong WaveNet baselines on automated and human evaluation metrics, and efficiently generate audio several orders of magnitude faster than their autoregressive counterparts.
View PDF on arXiv (opens in a new tab)

Diffusion-LM Improves Controllable Text Generation

A new non-autoregressive language model based on continuous diffusions that iteratively denoises a sequence of Gaussian vectors into word vectors, yielding a sequences of intermediate latent variables that enables a simple gradient-based algorithm to perform complex, controllable generation tasks.
View PDF on arXiv (opens in a new tab)

Towards GAN Benchmarks Which Require Generalization

A necessary condition for an evaluation metric not to behave this way is clarified: estimating the function must require a large sample from the model, so the resulting benchmarks cannot be "won" by training set memorization, while still being perceptually correlated and computable only from samples.
View PDF on arXiv (opens in a new tab)

ARGE S AMPLES

The problem of evaluating a generative model using only a finite sample from the model is studied, and the tradeoff between an evaluation function’s ability to permit meaningful generalization and its ability to be estimated from a finite samples is clarified.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)