43 citations · 153 across the 27 of their papers we have counts for
30 papers
Screener: Self-supervised Pathology Segmentation in Medical CT Images
Mikhail Goncharov, Eugenia Soboleva, Mariia Donskova +5
Accurate detection of all pathological findings in 3D medical images remains a significant challenge, as supervised models are limited to detecting only the few pathology classes a…
Selective Nonparametric Regression via Testing
Fedor Noskov, Alexander Fishkov, Maxim Panov
Prediction with the possibility of abstention (or selective prediction) is an important problem for error-critical machine learning applications. While well-studied in the classifi…
Optimal Noise Reduction in Dense Mixed-Membership Stochastic Block Models under Diverging Spiked Eigenvalues Condition
Fedor Noskov, Maxim Panov
Community detection is one of the most critical problems in modern network science. Its applications can be found in various fields, from protein modeling to social network analysi…
Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii +2
Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized. Despite recent advances in FL…
Scalable Batch Acquisition for Deep Bayesian Active Learning
Aleksandr Rubashevskii, Daria Kotova, Maxim Panov
In deep active learning, it is especially important to choose multiple examples to markup at each step to work efficiently, especially on large datasets. At the same time, existing…
Active Learning for Abstractive Text Summarization
Akim Tsvigun, Ivan Lysenko, Danila Sedashov +9
Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annot…
ScaleFace: Uncertainty-aware Deep Metric Learning
Roman Kail, Kirill Fedyanin, Nikita Muravev +2
The performance of modern deep learning-based systems dramatically depends on the quality of input objects. For example, face recognition quality would be lower for blurry or corru…
Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspective
Gleb Bazhenov, Sergei Ivanov, Maxim Panov +2
The problem of out-of-distribution detection for graph classification is far from being solved. The existing models tend to be overconfident about OOD examples or completely ignore…
Scalable computation of prediction intervals for neural networks via matrix sketching
Alexander Fishkov, Maxim Panov
Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains. Existing algorithms for uncertainty estimation requ…
Embedded Ensembles: Infinite Width Limit and Operating Regimes
Maksim Velikanov, Roman Kail, Ivan Anokhin +4
A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as E…
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Nikita Kotelevskii, Aleksandr Artemenkov, Kirill Fedyanin +6
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions. First, we show the principled way to measure the uncertainty…
Tensor-Train Density Estimation
Georgii S. Novikov, Maxim E. Panov, Ivan V. Oseledets
Estimation of probability density function from samples is one of the central problems in statistics and machine learning. Modern neural network-based models can learn high dimensi…
Assigning Topics to Documents by Successive Projections
Olga Klopp, Maxim Panov, Suzanne Sigalla +1
Topic models provide a useful tool to organize and understand the structure of large corpora of text documents, in particular, to discover hidden thematic structure. Clustering doc…
Monte Carlo Variational Auto-Encoders
Achille Thin, Nikita Kotelevskii, Arnaud Doucet +3
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better vari…
Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
Achille Thin, Nikita Kotelevskii, Christophe Andrieu +3
Markov Chain Monte Carlo (MCMC) is a class of algorithms to sample complex and high-dimensional probability distributions. The Metropolis-Hastings (MH) algorithm, the workhorse of…
EWS-GCN: Edge Weight-Shared Graph Convolutional Network for Transactional Banking Data
Ivan Sukharev, Valentina Shumovskaia, Kirill Fedyanin +2
In this paper, we discuss how modern deep learning approaches can be applied to the credit scoring of bank clients. We show that information about connections between clients based…
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling
Kirill Fedyanin, Evgenii Tsymbalov, Maxim Panov
Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-…
MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
Achille Thin, Nikita Kotelevskii, Jean-Stanislas Denain +4
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC). This approach can be used with g…
NCVis: Noise Contrastive Approach for Scalable Visualization
Aleksandr Artemenkov, Maxim Panov
Modern methods for data visualization via dimensionality reduction, such as t-SNE, usually have performance issues that prohibit their application to large amounts of high-dimensio…
Linking Bank Clients using Graph Neural Networks Powered by Rich Transactional Data
Valentina Shumovskaia, Kirill Fedyanin, Ivan Sukharev +2
Financial institutions obtain enormous amounts of data about user transactions and money transfers, which can be considered as a large graph dynamically changing in time. In this w…
Accuracy of Gaussian approximation in nonparametric Bernstein -- von Mises Theorem
Vladimir Spokoiny, Maxim Panov
The prominent Bernstein -- von Mises (BvM) result claims that the posterior distribution after centering by the efficient estimator and standardizing by the square root of the tota…
Geometry-Aware Maximum Likelihood Estimation of Intrinsic Dimension
Marina Gomtsyan, Nikita Mokrov, Maxim Panov +1
The existing approaches to intrinsic dimension estimation usually are not reliable when the data are nonlinearly embedded in the high dimensional space. In this work, we show that…
Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
Evgenii Tsymbalov, Sergei Makarychev, Alexander Shapeev +1
Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires eithe…
Constructing Graph Node Embeddings via Discrimination of Similarity Distributions
Stanislav Tsepa, Maxim Panov
The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science. In this work we propose a novel framework, which is aim…