@inproceedings{GregorovaDesaulesKalousis, author = {Gregorov{\´a}, Magda and Desaules, Marc and Kalousis, Alexandros}, title = {Learned transform compression with optimized entropy encoding}, series = {Neural Compression Workshop (CoRR)}, volume = {abs/2104.03305}, booktitle = {Neural Compression Workshop (CoRR)}, abstract = {We consider the problem of learned transform compression where we learn both, the transform as well as the probability distribution over the discrete codes. We utilize a soft relaxation of the quantization operation to allow for back-propagation of gradients and employ vector (rather than scalar) quantization of the latent codes. Furthermore, we apply similar relaxation in the code probability assignments enabling direct optimization of the code entropy. To the best of our knowledge, this approach is completely novel. We conduct a set of proof-of concept experiments confirming the potency of our approaches.}, language = {en} } @inproceedings{BogetGregorovaKalousis, author = {Boget, Yoann and Gregorov{\´a}, Magda and Kalousis, Alexandros}, title = {Permutation Equivariant Generative Adversarial Networks for Graphs}, series = {Neural Compression Workshop (CoRR)}, volume = {abs/2112.03621}, booktitle = {Neural Compression Workshop (CoRR)}, doi = {10.48550/arXiv.2112.03621}, abstract = {One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure the ordering invariance. After having discussed some properties of such functions, we propose 3G-GAN, a 3-stages model relying on GANs and equivariant functions. The model is still under development. However, we present some encouraging exploratory experiments and discuss the issues still to be addressed.}, language = {en} }