I
Ilya Tolstikhin
Researcher at Google
Publications - 41
Citations - 1736
Ilya Tolstikhin is an academic researcher from Google. The author has contributed to research in topics: Estimator & Kernel (statistics). The author has an hindex of 17, co-authored 40 publications receiving 1394 citations. Previous affiliations of Ilya Tolstikhin include Max Planck Society & Russian Academy of Sciences.
Papers
More filters
Proceedings Article
Wasserstein Auto-Encoders
TL;DR: The Wasserstein Auto-Encoder (WAE) is proposed---a new algorithm for building a generative model of the data distribution that shares many of the properties of VAEs (stable training, encoder-decoder architecture, nice latent manifold structure) while generating samples of better quality, as measured by the FID score.
Posted Content
Wasserstein Auto-Encoders
TL;DR: Wasserstein Auto-Encoder (WAE) as mentioned in this paper minimizes a penalized form of the Wasserstein distance between the model distribution and the target distribution, which leads to a different regularizer than the one used by the VAE.
Proceedings Article
AdaGAN: Boosting Generative Models
TL;DR: An iterative procedure, called AdaGAN, is proposed, where at every step the authors add a new component into a mixture model by running a GAN algorithm on a re-weighted sample by inspired by boosting algorithms.
Posted Content
MLP-Mixer: An all-MLP Architecture for Vision
Ilya Tolstikhin,Neil Houlsby,Alexander Kolesnikov,Lucas Beyer,Xiaohua Zhai,Thomas Unterthiner,Jessica Yung,Andreas Steiner,Daniel Keysers,Jakob Uszkoreit,Mario Lucic,Alexey Dosovitskiy +11 more
TL;DR: MLP-Mixer as discussed by the authors is an architecture based exclusively on multi-layer perceptrons (MLP), which contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with LSTM applied across patches, and it achieves competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-theart models.
Posted Content
From optimal transport to generative modeling: the VEGAN cookbook
Olivier Bousquet,Sylvain Gelly,Ilya Tolstikhin,Carl-Johann Simon-Gabriel,Bernhard Schoelkopf +4 more
TL;DR: It is shown that POT for the 2-Wasserstein distance coincides with the objective heuristically employed in adversarial auto-encoders (AAE) (Makhzani et al., 2016), which provides the first theoretical justification for AAEs known to the authors.