• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Samsung-HSE Laboratory

Publications
Article
Semi-Conditional Normalizing Flows for Semi-Supervised Learning

Atanov A., Volokhova A., Ashukha A. et al.

Working papers by Cornell University. Series math "arxiv.org". 2019.

Book chapter
Efficient Language Modeling with Automatic Relevance Determination in Recurrent Neural Networks

Kodryan M., Grachev A., Ignatov D. I. et al.

In bk.: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019). Iss. W19-43. Association for Computational Linguistics, 2019. P. 40-48.

Working paper
Variational Dropout via Empirical Bayes

Kharitonov V., Molchanov D., Vetrov D.

stat.ML. arxiv.org. Cornell University, 2018

Samsung-HSE Laboratory is a new research lab of the Faculty of Computer Science. The main direction of the Laboratory’s research is the construction of scalable probabilistic models. The core of the new Laboratory is a team of researchers of the Centre of Deep Learning and Bayesian Methods, with a broad expertise in the field of machine learning and Bayesian methods.

Samsung, which is one of the world's technological leaders, creates a network of joint laboratories around the world. The participation of HSE’s staff in this global project will allow them to focus on fundamental research and contact with the world's strongest research groups in the field of machine learning and artificial intelligence.

The major areas of research are:

  • Sparsification and acceleration of deep neural networks
  • Ensembles of ML algorithms
  • Uncertainty estimation and defences against adversarial attacks
  • Loss-based learning for Deep Structured Prediction
  • Stochastic optimization methods
  • Learning and inference methods for probabilistic models using tensor decomposition