Search Results for author:
Found 5 papers, 3 papers with code
Scalable Meta-Learning with Gaussian Processes
Meta-learning is a powerful approach that exploits historical data to quickly solve new tasks from the same distribution.
Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders
In this paper, we propose a simple and end-to-end trainable deterministic autoencoding framework, that efficiently shapes the latent space of the model during training and utilizes the capacity of expressive multi-modal latent distributions.
Transfer Learning with Gaussian Processes for Bayesian Optimization
Bayesian optimization is a powerful paradigm to optimize black-box functions based on scarce and noisy data.
Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation
Image generation has rapidly evolved in recent years.
Probabilistic Meta-Learning for Bayesian Optimization
Transfer and meta-learning algorithms leverage evaluations on related tasks in order to significantly speed up learning or optimization on a new problem.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
