YerevaNN /jɛɾɛvɑnˈɛn/ is a non-profit computer science and mathematics research lab based in Yerevan, Armenia.
Visit our blog and GitHub for more.
- Machine learning algorithms
-  Matching map recovery with an unknown number of outliers.
-  GradSkip: an extension of a local gradient method for distributed
optimization that supports variable number of local gradient steps in each communication round.
-  Characterization of the failure modes of domain generalization algorithms.
Published in CVPR'22
(with USC ISI).
-  WARP: a parameter-efficient method for transfer learning in NLP.
Published in ACL'21
(with USC ISI)
-  Theoretical analysis of the detection of the feature matching map in presence of outliers.
Published in Electronic Journal of Statistics
-  A survey of deep neural networks for semi-supervised image classification.
Published in JUCS.
-  Robust classification under class-dependent domain shift
(with USC ISI). Presented at ICML 2020
-  A novel robust estimator of the mean of a multivariate Gaussian distribution.
Published in Annals of Statistics
-  T-Corex: a novel method for temporal covariance estimation using information theoretic apparatus
(with USC ISI)
- Machine learning for biomedical data
- Development of Armenian treebanks
- Student projects
-  Morpheme-aware word vectors
-  A joint POS tagger and lemmatizer
-  Reproducing DIIN network for NLI
-  Reproducing R-NET network for QA
The handwritten digits in the background are generated by deep convolutional generative adversarial networks [paper] [code]