Publications

2024

2023

2022

2021

2020

2019

  • Structured Sparsification of Gated Recurrent Neural Networks by Ekaterina Lobacheva, Nadezhda Chirkova, Alexander Markovich, Dmitry Vetrov. Context and Compositionality in Biological and Artificial Neural Systems, NeurIPS 2019 Workshop
  • paper Unsupervised Domain Adaptation with Shared Latent Dynamics for Reinforcement Learning by Evgenii Nikishin, Arsenii Ashukha, Dmitry Vetrov. Bayesian Deep Learning, NeurIPS 2019 Workshop
  • Low-variance Gradient Estimates for the Plackett-Luce Distribution by Artyom Gadetsky, Kirill Struminsky, Christopher Robinson, Novi Quadrianto, Dmitry Vetrov. Bayesian Deep Learning, NeurIPS 2019 Workshop
  • Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning by Arsenii Ashukha, Alexander Lyzhov, Dmitry Molchanov, Dmitry Vetrov. Bayesian Deep Learning, NeurIPS 2019 Workshop
  • paper A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models by Maxim Kuznetsov, Daniil Polykovskiy, Dmitry Vetrov, Alexander Zhebrak. Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
  • papervideo A Simple Baseline for Bayesian Uncertainty in Deep Learning by Wesley Maddox, Timur Garipov, Pavel Izmailov, Dmitry Vetrov, Andrew Gordon Wilson. Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
  • paper The Implicit Metropolis-Hastings Algorithm by Kirill Neklyudov, Evgenii Egorov, Dmitry Vetrov. Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
  • papervideocode Importance Weighted Hierarchical Variational Inference by Artem Sobolev and Dmitry Vetrov. Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019)
  • papercode Deep learning enables rapid identification of potent DDR1 kinase inhibitors by Alex Zhavoronkov, Yan Ivanenkov, Alex Aliper, Mark Veselov, Vladimir Aladinskiy, Anastasiya Aladinskaya, Victor Terentiev, Daniil Polykovskiy, Maxim Kuznetsov, Arip Asadulaev, Yury Volkov, Artem Zholus, Rim Shayakhmetov, Alexander Zhebrak, Lidiya Minaeva, Bogdan Zagribelnyy, Lennart H. Lee, Richard Soll, David Madge, Li Xing, Tao Guo, Alán Aspuru-Guzik. Nature Biotechnology
  • papercode Subspace Inference for Bayesian Deep Learning by Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson. The 35th Uncertainty in Artificial Intelligence Conference (UAI 2019)
  • paper Semi-Conditional Normalizing Flows for Semi-Supervised Learning by Andrei Atanov, Alexandra Volokhova, Arsenii Ashukha, Ivan Sosnovik, Dmitry Vetrov. Workshop on Invertible Neural Nets and Normalizing Flows, International Conference on Machine Learning (ICML) 2019
  • papervideo Variational Autoencoder with Arbitrary Conditioning by Oleg Ivanov, Michael Figurnov, Dmitry Vetrov. Seventh International Conference on Learning Representations (ICLR 2019)
  • papervideocode Variance Networks: When Expectation Does Not Meet Your Expectations by Kirill Neklyudov, Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov. Seventh International Conference on Learning Representations (ICLR 2019)
  • papervideo The Deep Weight Prior by Andrei Atanov, Arsenii Ashukha, Kirill Struminsky, Dmitry Vetrov, Max Welling. Seventh International Conference on Learning Representations (ICLR 2019)
  • papervideo Doubly Semi-Implicit Variational Inference by Dmitry Molchanov, Valery Kharitonov, Artem Sobolev, Dmitry Vetrov. The 22st International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

2018

  • paper Probabilistic Adaptive Computation Time by Michael Figurnov, Artem Sobolev, Dmitry Vetrov. Bulletin of the Polish Academy of Sciences: Technical Sciences 2018
  • paper Bayesian Sparsification of Gated Recurrent Neural Networks by Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry Vetrov. Compact Deep Neural Network Representation with Industrial Applications NIPS 2018 Workshop
  • paper Joint Belief Tracking and Reward Optimization through Approximate Inference by Pavel Shvechikov, Alexander Grishin, Arseny Kuznetsov, Alexander Fritzler, Dmitry Vetrov. Reinforcement Learning under Partial Observability NeurIPS 2018 Workshop
  • paper Importance Weighted Hierarchical Variational Inference by Artem Sobolev and Dmitry Vetrov. Bayesian Deep Learning NIPS 2018 Workshop
  • paper Variational Dropout via Empirical Bayes by Valery Kharitonov, Dmitry Molchanov, Dmitry Vetrov. Bayesian Deep Learning NIPS 2018 Workshop
  • paper Subset-Conditioned Generation Using Variational Autoencoder With A Learnable Tensor-Train Induced Prior by Maksim Kuznetsov, Daniil Polykovskiy, Dmitry Vetrov, Alexander Zhebrak. Bayesian Deep Learning NIPS 2018 Workshop
  • paper Entangled Conditional Adversarial Autoencoder for de Novo Drug Discovery by Daniil Polykovskiy, Alexander Zhebrak, Dmitry Vetrov, Yan Ivanenkov, Vladimir Aladinskiy, Polina Mamoshina, Marine Bozdaganyan, Alexander Aliper, Alex Zhavoronkov, Artur Kadurin. Molecular Pharmaceutics Journal.
  • papervideo Quantifying Learning Guarantees for Convex but Inconsistent Surrogates by Kirill Struminsky, Simon Lacoste-Julien, Anton Osokin. Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018)
  • papervideocode Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs by Timur Garipov, Pavel Izmailov, Dmitry Podoprikhin, Dmitry Vetrov, Andrew Gordon Wilson. Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018)
  • paper Bayesian Compression for Natural Language Processing by Nadezhda Chirkova, Ekaterina Lobacheva, Dmitry Vetrov. 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)
  • paper Fast Uncertainty Estimates and Bayesian Model Averaging of DNNs by Wesley Maddox, Timur Garipov, Pavel Izmailov, Dmitry Vetrov, Andrew Gordon Wilson. Uncertainty in Artificial Intelligence Workshop (UAI Workshop) 2018
  • paper Improving Stability in Deep Reinforcement Learning with Weight Averaging by Evgenii Nikishin, Pavel Izmailov, Ben Athiwaratkun, Dmitrii Podoprikhin, Timur Garipov, Pavel Shvechikov, Dmitry Vetrov, Andrew Gordon Wilson. Uncertainty in Artificial Intelligence Workshop (UAI Workshop) 2018
  • paper Averaging Weights Leads to Wider Optima and Better Generalization by Pavel Izmailov, Dmitry Podoprikhin, Timur Garipov, Dmitry Vetrov, Andrew Gordon Wilson. Conference on Uncertainty in Artificial Intelligence 2018 (UAI 2018)
  • paper Conditional Generators of Words Definitions by Artyom Gadetsky, Ilya Yakubovskiy, Dmitry Vetrov. 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)
  • paper SEARNN: Training RNNs with global-local losses by Rémi Leblond, Jean-Baptiste Alayrac, Anton Osokin, Simon Lacoste-Julien. International Conference on Learning Representations (ICLR) 2018
  • paper Concorde: Morphological Agreement in Conversational Models by Daniil Polykovskiy, Dmitry Soloviev, Sergey Nikolenko. 10th Asian Conference on Machine Learning (ACML 2018)
  • paper ReSet: Learning Recurrent Dynamic Routing in ResNet-like Neural Networks by Iurii Kemaev, Daniil Polykovskiy, Dmitry Vetrov. 10th Asian Conference on Machine Learning (ACML 2018)
  • paper Expressive power of recurrent neural networks by Valentin Khrulkov, Alexander Novikov, Ivan Oseledets. Sixth International Conference on Learning Representations (ICLR 2018)
  • paper Fast Adaptation in Generative Models with Generative Matching Networks by Sergey Bartunov and Dmitry P. Vetrov. The 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018
  • paper Scalable Gaussian Processes with Billions of Inducing Inputs via Tensor Train Decomposition by Pavel Izmailov, Alexander Novikov, Dmitry Kropotov. The 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018
  • paper Predictive model for bottomhole pressure based on machine learning by Pavel Spesivtsev, Konstantin Sinkov, Ivan Sofronov, Anna Zimina, Alexey Umnov, Ramil Yarullin, Dmitry Vetrov. Journal of Petroleum Science and Engineering
  • papervideo Uncertainty Estimation via Stochastic Batch Normalization by Andrei Atanov, Arsenii Ashukha, Dmitry Molchanov, Kirill Neklyudov, Dmitry Vetrov. International Conference on Learning Representations Workshop (ICLR Workshop) 2018
  • paper Bayesian Incremental Learning for Deep Neural Networks by Max Kochurov, Timur Garipov, Dmitry Podoprikhin, Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov. International Conference on Learning Representations Workshop (ICLR Workshop) 2018
  • paper Monotonic models for real-time dynamic malware detection by Alexander Chistyakov, Ekaterina Lobacheva, Alexander Shevelev, Alexey Romanenko. International Conference on Learning Representations Workshop (ICLR Workshop) 2018

2017

  • paper Exponential Machines by Alexander Novikov, Mikhail Trofimov, Ivan Oseledets. Bulletin of the Polish Academy of Sciences: Technical Sciences 2018
  • papervideocode Structured Bayesian Pruning via Log-Normal Multiplicative Noise by Kirill Neklyudov, Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov. Thirty-first Conference on Neural Information Processing Systems (NIPS 2017)
  • papervideo Spatially Adaptive Computation Time for Residual Networks by Michael Figurnov, Maxwell Collins, Yukun Zhu, Li Zhang, Jonathan Huang, Dmitry Vetrov, Ruslan Salakhutdinov. Conference on Computer Vision and Pattern Recognition 2017 (CVPR 2017)
  • papervideocode Variational Dropout Sparsifies Deep Neural Networks by Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov. International Conference on Machine Learning (ICML 2017)
  • paper Bayesian Sparsification of Recurrent Neural Networks by Ekaterina Lobacheva, Nadezhda Chirkova, Dmitry Vetrov. International Conference on Machine Learning (ICML) Workshop 2017
  • paper Fast Adaptation in Generative Models with Generative Matching Networks by Sergey Bartunov and Dmitry P. Vetrov. International Conference on Learning Representations (ICLR) Workshop 2017
  • paper Semantic embeddings for program behaviour patterns by Alexander Chistyakov, Ekaterina Lobacheva, Arseny Kuznetsov, Alexey Romanenko. International Conference on Learning Representations (ICLR) Workshop 2017

2016

  • paper A Superlinearly-Convergent Proximal Newton-Type Method for the Optimization of Finite Sums by Anton Rodomanov and Dmitry Kropotov. International Conference on Machine Learning (ICML) 2016
  • paper One-shot Learning with Memory-Augmented Neural Networks by Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, Timothy Lillicrap. International Conference on Machine Learning (ICML) 2016
  • paper Breaking Sticks and Ambiguities with Adaptive Skip-gram by Sergey Bartunov, Dmitry Kondrashkin, Anton Osokin, Dmitry Vetrov. International Conference on Artificial Intelligence and Statistics (AISTATS) 2016
  • paper Deep Part-Based Generative Shape Model with Latent Variables by Alexander Kirillov, Mikhail Gavrikov, Ekaterina Lobacheva, Anton Osokin, Dmitry Vetrov. British Machine Vision Conference 2016 (BMVC 2016)
  • paper A New Approach for Sparse Bayesian Channel Estimation in SCMA Uplink Systems by Kirill Struminsky, Stanislav Kruglik, Dmitry Vetrov, Ivan Oseledets. International Conference on Wireless Communications and Signal Processing (WCSP) 2016
  • paper Tensor Train polynomial model via Riemannian optimization by Alexander Novikov, Mikhail Trofimov, Ivan Oseledets. (ICML) 2016. Advances in non-convex analysis and optimization Workshop
  • paper PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions by Michael Figurnov, Dmitry Vetrov, Pushmeet Kohli. International Conference on Learning Representations (ICLR) 2016 Workshop track
  • paper Dropout-based Automatic Relevance Determination by Dmitry Molchanov, Arseniy Ashuha, Dmitry Vetrov. Advances in Neural Information Processing Systems (NIPS) 2016
  • paper Robust Variational Inference by Michael Figurnov, Kirill Struminsky, Dmitry Vetrov. Advances in Neural Information Processing Systems (NIPS) 2016
  • paper Ultimate tensorization: convolutions and FC alike by Timur Garipov, Dmitry Podoprikhin, Alexander Novikov, Dmitry Vetrov. Advances in Neural Information Processing Systems (NIPS) 2016

2015

  • paper A Newton-type Incremental Method with a Superlinear Convergence Rate by A. Rodomanov and D. Kropotov. NIPS 2015 Workshop on Optimization for Machine Learning
  • paper Inferring M-Best Diverse Labelings in a Single One by A. Kirillov, B. Savchynskyy, D. Schlesinger, D. Vetrov, C. Rother. Proceedings of the International Conference on Computer Vision (ICCV). 2015
  • paper Joint Optimization of Segmentation and Color Clustering by Ekaterina Lobacheva, Olga Veksler, Yuri Boykov. 2015 International Conference on Computer Vision (ICCV 2015)
  • paper Tensorizing Neural Networks by Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, Dmitry Vetrov. In Advances in Neural Information Processing Systems 28 (NIPS). 2015
  • paper M-Best-Diverse Labelings for Submodular Energies and Beyond by A. Kirillov, D. Schlesinger, D. Vetrov, C. Rother, B. Savchynskyy. In Advances in Neural Information Processing Systems 28 (NIPS). 2015
  • paper Multi-utility Learning: Structured-output Learning with Multiple Annotation-specific Loss Functions by R. Shapovalov, A. Osokin, D. Vetrov, P. Kohli. In Proceedings of International Workhop on Energy Minimization Methods (EMMCVPR2015), 2015
  • paper Learning representations in directed networks by Oleg Ivanov and Sergey Bartunov. 4th Conference on Analysis of Images, Social Networks, and Texts (AIST), 2015. Best conference paper award

2014

  • paper IEEE Transactions on Pattern Analysis and Machine Intelligence by A. Osokin and D. Vetrov. Submodular relaxation for inference in Markov random fields. (TPAMI). Accepted. 2014
  • paper Perceptually Inspired Layout-aware Losses for Image Segmentation by A. Osokin and P. Kohli. European Conference on Computer Vision (ECCV), 2014
  • paper Variational Inference for Sequential Distance Dependent Chinese Restaurant Process by S. Bartunov and D. Vetrov. Proceedings of the 31st International Conference on Machine Learning, Beijing, China, 2014. JMLR: W&CP volume 32
  • paper Putting MRFs on a Tensor Train by A. Novikov, A. Rodomanov, A. Osokin, D. Vetrov. Proceedings of the 31st International Conference on Machine Learning, Beijing, China, 2014. JMLR: W&CP volume 32

2013

  • paper Learning a Model for Shape-Constrained Image Segmentation from Weakly Labeled Data by B. Yangel and D. Vetrov. In Proceedings of International Workhop on Energy Minimization Methods (EMMCVPR2013), 2013
  • paper In Computer Vision and Pattern Recognition by R. Shapovalov, D. Vetrov, P. Kohli. Spatial Inference Machines. (CVPR), 2013
  • paper A Principled Deep Random Field Model for Image Segmentation by P. Kohli, A. Osokin, S. Jegelka. In Computer Vision and Pattern Recognition (CVPR), 2013
  • paper Automatic Determination of Cell Division Rate Using Microscope Images by K. Nekrasov, D. Laptev, D. Vetrov. Pattern Recognition and Image Analysis, 23(1):1–6, 2013
  • paper An Approach to Segmentation of Mouse Brain Imagesvia Intermodal Registration by P. Voronin, D. Vetrov, K. Ismailov. Pattern Recognition and Image Analysis, 23(2):335–339, 2013

2012

  • paper Fast Approximate Energy Minimization with Label Costs by A. Delong, A. Osokin, H. Isack, Y. Boykov. International Journal of Computer Vision (IJCV), 96(1):1–27, 2012
  • paper Submodular Relaxation for MRFs with High-Order Potentials by A. Osokin and D. Vetrov. HiPot: ECCV 2012 Workshop on Higher-Order Models and Global Constraints in Computer Vision, 2012
  • paper Minimizing Sparse High-Order Energies by Submodular Vertex-Cover by A. Delong, O. Veksler, A. Osokin, Y. Boykov. Advances in Neural Information Processing Systems (NIPS), 2012

2011

  • paper MRF Energy Minimization Approach with Epitomic Textural Global Term for Image Segmentation Problems by D. Elshin and D. Kropotov. In Proceedings of Bilateral Russian-Indian Workshop on Emerging Applications of Computer Vision, 2011
  • paper Submodular Decomposition Framework for Inference in Associative Markov Networks with Global Constraints by A. Osokin, D. Vetrov, V. Kolmogorov. Proceedings ofInternational Conference on Computer Vision and Pattern Recognition (CVPR), 2011
  • paper Image Segmentation with a Shape Prior Based on Simplified Skeleton by B. Yangel and D. Vetrov. Proceedings of International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR), LNCS 6819, 2011
  • paper Graph Preserving Label Decomposition in Discrete MRFs with Selfish Potentials by D. Vetrov and A. Osokin. Proceedings of NIPS Workshop on Discrete Optimization in Machine learning (DISCML NIPS), 2011
  • paper An Interactive Method of Anatomical Segmentation and Gene Expression Estimation for an Experimental Mouse Brain Slice by A. Osokin, D. Vetrov, A. Lebedev, V. Galatenko, D. Kropotov, K. Anokhin. Lecture Notes in Computer Science (LNCS), vol. 6685, pp. 86–97, 2011

2010

  • paper Fast Approximate Energy Minimization with Label Costs by A. Delong, A. Osokin, H. Isack, Y. Boykov. Proceedings of International Conference on Computer Vision and Pattern Recognition (CVPR), 2010
  • paper Variational Relevance Vector Machine for Tabular Data by D. Kropotov, D. Vetrov, L. Wolf, T. Hassner. Proceedings of Asian Conference on Machine Learning (ACML), JMLR Workshop & Conference Proceedings, vol. 13, pp. 79-94, 2010
  • paper The Algorithm for Detection of Fuzzy Behavioral Patterns by V. Vishnevsky and D. Vetrov. Proceedings of International Conference on Methods and Techniques in Behavioral Research, ISBN 978-90-74821-86-5, 2010
  • paper 3D Reconstruction of Mouse Brain from a Sequence of 2D Brain Slices in Application to Allen Brain Atlas by A. Osokin, D. Vetrov, D. Kropotov. Lecture Notes in Computer Science (LNCS), vol. 6160, pp. 291-303, 2010
  • paper Variational Segmentation Algorithms with Label Frequency Constraints by D. Kropotov, D. Laptev, A. Osokin, D. Vetrov. Pattern Recognition and Image Analysis, vol. 20, no. 3, pp. 324-334, 2010
  • paper Intermodal Registration Algorithm for Segmentation of Mouse Brain Images by P. Voronin and D. Vetrov. Proceedings of International Conference on Pattern Recognition and Image Analysis (PRIA), vol. 2, pp. 377-381, 2010
  • paper Automatic Detection of Cell Division Intensity in Budding Yeast by K. Nekrasov, D. Laptev, D. Vetrov. Proceedings of International Conference on Pattern Recognition and Image Analysis (PRIA), vol. 2, pp. 335-339, 2010

2009

  • paper Relevant Regressors Selection by Continuous AIC by D. Kropotov, N. Ptashko, D. Vetrov. Pattern Recognition and Image Analysis, vol. 19, no. 3, pp. 456-464, 2009
  • paper General Solutions for Information-Based and Bayesian Approaches to Model Selection in Linear Regression and Their Equivalence by D. Kropotov and D. Vetrov. Pattern Recognition and Image Analysis, vol. 19, no. 3, pp. 447-455, 2009
  • paper Video Tracking and Behaviour Segmentation of Laboratory Rodents by E. Lomakina-Rumyantseva, P. Voronin, D. Kropotov, D. Vetrov, A. Konushin. Pattern Recognition and Image Analysis, vol. 19, no. 4, pp. 616-622, 2009

2008

  • paper An Automatic Relevance Determination Procedure Based on Akaike Information Criterion for Linear Regression Problems by D. Kropotov and D. Vetrov. Proceedings of ICML Workshop on Sparse Optimization and Variable Selection, 2008
  • paper Automatic segmentation of mouse behavior using hidden markov models by D. Vetrov, D. Kropotov, A. Konushin, E. Lomakina-Rumyantseva, I. Zarayskaya, K. Anokhin. Proceedings of International Conference on Methods and Techniques in Behavioral Research, 2008
  • paper Automated distinguishing of mouse behavior in new environment and under amphetamine using decision trees by A. Konushin, E. Lomakina-Rumyantseva, D. Kropotov, D. Vetrov, A. Cherepov, K. Anokhin. Proceedings of International Conference on Methods and Techniques in Behavioral Research, 2008

2007

  • paper On One Method of Non-Diagonal Regularization in Sparse Bayesian Learning by D. Kropotov and D. Vetrov. Proceedings of International Conference on Machine Learning (ICML), pp. 457-464, 2007
  • paper Fuzzy Rules Generation Method for Pattern Recognition Problems by D. Kropotov and D. Vetrov. Lecture Notes in Computer Science (LNCS), vol. 4578, pp. 203–210, 2007