Header logo is

3 results (View BibTeX file of all listed publications)

2019

no image
Variational Autoencoders Recover PCA Directions (by Accident)

Rolinek, M., Zietlow, D., Martius, G.

In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

Abstract
The Variational Autoencoder (VAE) is a powerful architecture capable of representation learning and generative modeling. When it comes to learning interpretable (disentangled) representations, VAE and its variants show unparalleled performance. However, the reasons for this are unclear, since a very particular alignment of the latent embedding is needed but the design of the VAE does not encourage it in any explicit way. We address this matter and offer the following explanation: the diagonal approximation in the encoder together with the inherent stochasticity force local orthogonality of the decoder. The local behavior of promoting both reconstruction and orthogonality matches closely how the PCA embedding is chosen. Alongside providing an intuitive understanding, we justify the statement with full theoretical analysis as well as with experiments.

al

arXiv link (url) Project Page [BibTex]

2019

al Rolinek, M., Zietlow, D., Martius, G. Variational Autoencoders Recover PCA Directions (by Accident) In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2019, June 2019 (inproceedings)

arXiv link (url) Project Page [BibTex]

no image
Control What You Can: Intrinsically Motivated Task-Planning Agent

Blaes, S., Vlastelica, M., Zhu, J., Martius, G.

In Advances in Neural Information Processing (NeurIPS’19), Curran Associates, Inc., NeurIPS'19, 2019 (inproceedings)

Abstract
We present a novel intrinsically motivated agent that learns how to control the environment in the fastest possible manner by optimizing learning progress. It learns what can be controlled, how to allocate time and attention, and the relations between objects using surprise based motivation. The effectiveness of our method is demonstrated in a synthetic as well as a robotic manipulation environment yielding considerably improved performance and smaller sample complexity. In a nutshell, our work combines several task-level planning agent structures (backtracking search on task graph, probabilistic road-maps, allocation of search efforts) with intrinsic motivation to achieve learning from scratch.

al

link (url) [BibTex]

al Blaes, S., Vlastelica, M., Zhu, J., Martius, G. Control What You Can: Intrinsically Motivated Task-Planning Agent In Advances in Neural Information Processing (NeurIPS’19), Curran Associates, Inc., NeurIPS'19, 2019 (inproceedings)

link (url) [BibTex]

no image
Analytical classical density functionals from an equation learning network

Lin, S., Martius, G., Oettel, M.

2019, arXiv preprint \url{https://arxiv.org/abs/1910.12752} (misc)

al

[BibTex]

al Lin, S., Martius, G., Oettel, M. Analytical classical density functionals from an equation learning network 2019, arXiv preprint \url{https://arxiv.org/abs/1910.12752} (misc)

[BibTex]