• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Variational Autoencoder with Arbitrary Conditioning
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
June 5, 2026
Neural Network Maps as a Method for Constructing Mathematical Models
Scientists from HSE University–Nizhny Novgorod and the Institute of Physics Belgrade, Serbia, are jointly exploring the application of machine learning techniques and neural networks to the study of nonlinear dynamics. Natalya Stankevich, Leading Research Fellow at the Laboratory of Topological Methods in Dynamics of the Faculty of Informatics, Mathematics, and Computer Science at HSE University–Nizhny Novgorod, spoke to the HSE News Service about this international project.
June 5, 2026
‘In the Age of Technology, It Is Interesting to Look into the Past and Think about What We Can Take from It
Polina Tabakova decided to apply for a Philology degree at HSE in Nizhny Novgorod because she grew up in Mari El and did not want to move far away from the Russian forests. In an interview for the Young Scientists of HSE University project, she spoke about the genre of the campus novel, the existential drama of Kolobok, and a blackout version of Eugene Onegin.
June 5, 2026
HSE Scientists Develop Method to Compress Large Language Models Without Losing Quality
Researchers from the AI and Digital Science Institute at the HSE Faculty of Computer Science have developed a new compression method for large language models such as GPT and LLaMA that reduces their size by 25–36% without additional training or significant loss of accuracy. This is the first approach to use mathematical transformations—specifically, rotations of model weights—to make models more amenable to compression with structured matrices. The study results have been published in ACL Findings 2025. The code is available on GitHub.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Variational Autoencoder with Arbitrary Conditioning

P. 1–25.
Vetrov D., Ivanov O.

We propose a single neural probabilistic model based on variational autoencoder that can be conditioned on an arbitrary subset of observed features and then sample the remaining features in "one shot". The features may be both real-valued and categorical. Training of the model is performed by stochastic variational Bayes. The experimental evaluation on synthetic data, as well as feature imputation and image inpainting problems, shows the effectiveness of the proposed approach and diversity of the generated samples.

Language: English
Text on another site
Keywords: «обучение без учителя»Unsupervised learninginpaintingvariational autoencodergenerative modelsгенеративные модели

In book

Proceedings of the 7th International Conference on Learning Representations (ICLR 2019)
ICLR, 2019.
Similar publications
Transformer-based approaches for lemmatizing abbreviations in Russian texts
Glazkova A., Lyashevskaya O., Morozov D. et al., Journal of Mathematical Sciences 2025 Vol. 546 P. 32–47
This paper addresses the task of lemmatizing abbreviations in the Russian language. Abbreviation lemmatization is particularly challenging, as it involves not only transforming a word into its normal form but also correctly expanding the abbreviation. We explore two approaches to this task, both leveraging large pretrained language models. The first approach is generative, where the ...
Added: March 10, 2026
Learning to hear broken motors: Signature-guided data augmentation for induction motor diagnostics
Ali S., Khizhik A., Svirin S. et al., Engineering Applications of Artificial Intelligence 2025 Vol. 170 Article 114137
The application of machine learning algorithms in the intelligent diagnosis of three-phase engine has the potential to significantly enhance diagnostic performance and accuracy. Traditional methods largely rely on signature analysis, which, despite being a standard practice, can benefit from the integration of advanced machine learning techniques. In our study, we innovate by combining machine learning ...
Added: February 16, 2026
Диффузионные модели для генерации синтетических табличных данных
Телешева Э. Д., Hushchyn M., Доклады Российской академии наук. Математика, информатика, процессы управления (ранее - Доклады Академии Наук. Математика) 2025 Т. 527 № S С. 388–399
he problem of generating high-quality synthetic data is crucial for many data science tasks. A generated dataset can cut the costs on the augmentation of the existing data with additional instances, for example, in physics, or help with its privacy protection, for instance, in banking. However, generating a tabular dataset is challenging, as the data ...
Added: February 12, 2026
From Patterns to Predictions: A Shapelet-Based Framework for Directional Forecasting in Noisy Financial Markets
Kim J., Lee H., Jeon H. et al., , in: CIKM '25: Proceedings of the 34rd ACM International Conference on Information and Knowledge Management.: ACM, 2025. P. 1344–1353.
Directional forecasting in financial markets requires both accuracy and interpretability. Before the advent of deep learning, interpretable approaches based on human-defined patterns were prevalent, but their structural vagueness and scale ambiguity hindered generalization. In contrast, deep learning models can effectively capture complex dynamics, yet often offer limited transparency. To bridge this gap, we propose a ...
Added: November 21, 2025
Revisiting Non-Acyclic GFlowNets in Discrete Environments
Morozov N., Maximov I., Tiapkin D. et al., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 44887–44910.
Generative Flow Networks (GFlowNets) are a family of generative models that learn to sample objects from a given probability distribution, potentially known up to a normalizing constant. Instead of working in the object space, GFlowNets proceed by sampling trajectories in an appropriately constructed directed acyclic graph environment, greatly relying on the acyclicity of the graph. ...
Added: October 15, 2025
Новые интерфейсы и новые медиаторы
Maksimenkova O. V., Сегал А. П., Вопросы философии 2025 № 10 С. 67–76
The study is devoted to the humans and artificial intelligence (AI) interaction. The authors view this interaction as mediated by interfaces that both simplify it and hide the real mechanisms of encoding and decoding messages (according to Shannon). In such a situation, the characteristics of the actor of communication are blurred, and it is not ...
Added: October 2, 2025
Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V
Cham: Springer, 2025.
This book constitutes the refereed proceedings of 34th International Workshops which were held in conjunction with the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025.   The 20 full papers and 8 abstracts included in this workshop volume were carefully reviewed and selected from 42 submissions. ...
Added: September 29, 2025
Generative models and seq2seq techniques for the flash-simulation of the LHCb experiment
Derkach D., Anderlini L., Capelli S. et al., Proceedings of Science 2025 Vol. 476 P. 1032
Simulating detector and reconstruction effects on physics quantities is crucial for data analysis, but it is coming unsustainably costly for the upcoming HEP experiments. The most radical approach to speed-up detector simulation is Flash Simulation, as proposed by the LHCb collaboration in Lamarr, a software package implementing a novel simulation paradigm relying on Deep Generative ...
Added: March 13, 2025
Data augmentation with generative models improves detection of Non-B DNA structures
Cherednichenko O., Poptsova M., Computers in Biology and Medicine 2025 Vol. 184 Article 109440
Non-B DNA structures, or flipons, are important functional elements that regulate a large spectrum of cellular programs. Experimental technologies for flipon detection are limited to the subsets that are active at the time of an experiment and cannot capture whole-genome functional set. Thus, the task of generating reliable whole-genome annotations of non-B DNA structures is ...
Added: March 11, 2025
The LHCb ultra-fast simulation option, Lamarr design and validation
Derkach D., Kazeev N., Mokhnenko S. et al., EPJ Web of Conferences 2024 Vol. 295 P. 03040
Detailed detector simulation is the major consumer of CPU resources at LHCb, having used more than 90% of the total computing budget during Run 2 of the Large Hadron Collider at CERN. As data is collected by the upgraded LHCb detector during Run 3 of the LHC, larger requests for simulated data samples are necessary, ...
Added: January 8, 2025
ЛИНГВОДИДАКТИЧЕСКИЙ АСПЕКТ ЦИФРОВОЙ КОМПЕТЕНЦИИ ПРЕПОДАВАТЕЛЯ ИНОСТРАННЫХ ЯЗЫКОВ: ТРАНСФОРМАЦИИ И АКТУАЛЬНОСТЬ
Solomonova A., Садекова С. Р., Русский язык за рубежом 2024 № 3 (304) С. 95–99
This article examines the importance of digital competence of foreign language teachers in modern education. It analyses the advantages of using digital technologies in the educational process and the necessity for teachers to master the tools of digital information processing. Particular attention is paid to the linguodidactic aspect of digital competence, including the development of ...
Added: October 29, 2024
Исследование потенциала генеративных моделей для оценивания эссе и обеспечения обратной связи
Bogolepova S., Жаркова М. Г., Отечественная и зарубежная педагогика 2024 Т. 1 № 5(101) С. 123–137
In the era of rapid development of generative language models these tools are increasingly being used by both students and instructors. This paper aims to investigate the potential of generative models interacting with users via chatbots ChatGPT и PerplexityAI for the evaluation of standardised essays in English and the provision of feedback on their quality. ...
Added: October 28, 2024
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
Bobkov D., Titov V., Alanov A. et al., , in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.: IEEE, 2024. P. 9337–9346.
The task of manipulating real image attributes through StyleGAN inversion has been extensively researched. This process involves searching latent variables from a well-trained StyleGAN generator that can synthesize a real image modifying these latent variables and then synthesizing an image with the desired edits. A balance must be struck between the quality of the reconstruction ...
Added: July 10, 2024
Soft Margin Spectral Normalization for GANs
Rogachev A., Ratnikov F., Computing and Software for Big Science 2024 Vol. 8 No. 1 Article 12
In this paper, we explore the use of Generative Adversarial Networks (GANs) to speed up the simulation process while ensuring that the generated results are consistent in terms of physics metrics. Our main focus is the application of spectral normalization for GANs to generate electromagnetic calorimeter (ECAL) response data, which is a crucial component of ...
Added: July 2, 2024
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit