no code implementations • 12 Oct 2021 • Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gaiński, Jacek Tabor, Igor Podolak, Paweł Morkisz, Stanisław Jastrzębski
Self-supervised learning holds promise to revolutionize molecule property prediction - a central task to drug discovery and many more industries - by enabling data efficient learning from scarce experimental data.
1 code implementation • NeurIPS 2021 • Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński
The problem of reducing processing time of large deep learning models is a fundamental challenge in many real-world applications.
1 code implementation • 15 Sep 2020 • Szymon Knop, Marcin Mazur, Przemysław Spurek, Jacek Tabor, Igor Podolak
First, an autoencoder based architecture, using kernel measures, is built to model a manifold of data.
1 code implementation • 30 May 2019 • Przemysław Spurek, Szymon Knop, Jacek Tabor, Igor Podolak, Bartosz Wójcik
Several deep models, esp.
no code implementations • ICLR 2019 • Damian Leśniak, Igor Sieradzki, Igor Podolak
We investigate the properties of multidimensional probability distributions in the context of latent space prior distributions of implicit generative models.
no code implementations • 29 Jan 2019 • Szymon Knop, Marcin Mazur, Jacek Tabor, Igor Podolak, Przemysław Spurek
In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach.
no code implementations • 5 Jun 2018 • Damian Leśniak, Igor Sieradzki, Igor Podolak
We investigate the properties of multidimensional probability distributions in the context of latent space prior distributions of implicit generative models.
2 code implementations • ICLR 2019 • Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski
The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE.