Skip to search formSkip to main contentSkip to account menu
InfoVAE: Information Maximizing Variational Autoencoders
TLDR
It is shown that this model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution, and it is demonstrated that the models outperform competing approaches on multiple performance metrics.
View PDF on arXiv
Denoising Diffusion Implicit Models
TLDR
Denoising diffusion implicit models (DDIMs) are presented, a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs that can produce high quality samples faster and perform semantically meaningful image interpolation directly in the latent space.
View PDF on arXiv
InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
TLDR
A new algorithm is proposed that can infer the latent structure of expert demonstrations in an unsupervised way, built on top of Generative Adversarial Imitation Learning, and can not only imitate complex behaviors, but also learn interpretable and meaningful representations of complex behavioral data, including visual demonstrations.
View Paper
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
TLDR
It is shown that the proposed Info-VAE model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution.
View via Publisher
Understanding the Limitations of Variational Mutual Information Estimators
TLDR
A new estimator is developed that focuses on variance reduction and theoretically shows that, under some conditions, estimators such as MINE exhibit variance that could grow exponentially with the true amount of underlying MI.
View PDF on arXiv
Multi-Agent Generative Adversarial Imitation Learning
TLDR
This work proposes a new framework for multi-agent imitation learning for general Markov games, where a generalized notion of inverse reinforcement learning is built upon, and introduces a practical multi- agent actor-critic algorithm with good empirical performance.
View PDF on arXiv
Learning Hierarchical Features from Deep Generative Models
TLDR
It is proved that hierarchical latent variable models do not take advantage of the hierarchical structure when trained with some existing variational methods, and some limitations on the kind of features existing models can learn are provided.
View Paper
A-NICE-MC: Adversarial Training for MCMC
TLDR
A-NICE-MC provides the first framework to automatically design efficient domain-specific Markov Chain Monte Carlo proposals, and is able to significantly outperform competing methods such as Hamiltonian Monte Carlo.
View PDF on arXiv
A Theory of Usable Information Under Computational Constraints
TLDR
Predictive $\mathcal{V}$-information is more effective than mutual information for structure learning and fair representation learning and by incorporating computational constraints, can be reliably estimated from data even in high dimensions with PAC-style guarantees.
View PDF on arXiv
Towards Deeper Understanding of Variational Autoencoding Models
TLDR
A new sequential VAE model that can generate sharp samples on the LSUN image dataset based on pixel-wise reconstruction loss is proposed, and an optimization criterion is proposed that encourages unsupervised learning of informative latent features.
View PDF on arXiv
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License