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

Samsung-HSE Laboratory

Publications
Article
A randomized coordinate descent method with volume sampling

Rodomanov A., Kropotov D.

SIAM Journal on Optimization. 2020. Vol. 30. No. 3. P. 1878-1904.

Book chapter
Deterministic Decoding for Discrete Data in Variational Autoencoders

Polykovskiy D., Vetrov D.

In bk.: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108. Iss. 108. PMLR, 2020. P. 3046-3056.

Working paper
MARS: Masked Automatic Ranks Selection in Tensor Decompositions

Kodryan M., Kropotov D., Vetrov D.

First Workshop on Quantum Tensor Networks in Machine Learning, NeurIPS 2020. QTNML 2020. First Workshop on Quantum Tensor Networks in Machine Learning, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020

Samsung-HSE Laboratory is a 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