Publications

2018

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

2017

2016

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

2015

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

2014

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

2013

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

2012

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

2011

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

2010

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

2009

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

2008

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

2007

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