1 code implementation • ACL 2022 • Artem Vazhentsev, Gleb Kuzmin, Artem Shelmanov, Akim Tsvigun, Evgenii Tsymbalov, Kirill Fedyanin, Maxim Panov, Alexander Panchenko, Gleb Gusev, Mikhail Burtsev, Manvel Avetisian, Leonid Zhukov
Uncertainty estimation (UE) of model predictions is a crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, out-of-distribution detection, etc.
no code implementations • 18 Mar 2024 • Maksim Velikanov, Maxim Panov, Dmitry Yarotsky
In the present work, we consider the training of kernels with a family of $\textit{spectral algorithms}$ specified by profile $h(\lambda)$, and including KRR and GD as special cases.
no code implementations • 7 Mar 2024 • Ekaterina Fadeeva, Aleksandr Rubashevskii, Artem Shelmanov, Sergey Petrakov, Haonan Li, Hamdy Mubarak, Evgenii Tsymbalov, Gleb Kuzmin, Alexander Panchenko, Timothy Baldwin, Preslav Nakov, Maxim Panov
Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output.
no code implementations • 16 Feb 2024 • Nikita Kotelevskii, Maxim Panov
Distinguishing sources of predictive uncertainty is of crucial importance in the application of forecasting models across various domains.
no code implementations • 25 Dec 2023 • Vincent Plassier, Nikita Kotelevskii, Aleksandr Rubashevskii, Fedor Noskov, Maksim Velikanov, Alexander Fishkov, Samuel Horvath, Martin Takac, Eric Moulines, Maxim Panov
Conformal Prediction (CP) stands out as a robust framework for uncertainty quantification, which is crucial for ensuring the reliability of predictions.
no code implementations • 18 Dec 2023 • Nikita Kotelevskii, Samuel Horváth, Karthik Nandakumar, Martin Takáč, Maxim Panov
This paper presents a new approach to federated learning that allows selecting a model from global and personalized ones that would perform better for a particular input point.
no code implementations • 13 Nov 2023 • Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, Artem Shelmanov
Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields.
no code implementations • 28 Sep 2023 • 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.
no code implementations • 26 Jul 2023 • Fedor Noskov, Maxim Panov
Community detection is one of the most critical problems in modern network science.
no code implementations • 8 Jun 2023 • Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines, Maxim Panov
Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized.
1 code implementation • 13 Jan 2023 • 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.
1 code implementation • 9 Jan 2023 • Akim Tsvigun, Ivan Lysenko, Danila Sedashov, Ivan Lazichny, Eldar Damirov, Vladimir Karlov, Artemy Belousov, Leonid Sanochkin, Maxim Panov, Alexander Panchenko, Mikhail Burtsev, Artem Shelmanov
Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance.
no code implementations • 2 Jan 2023 • Asma Ahmed Hashmi, Aigerim Zhumabayeva, Nikita Kotelevskii, Artem Agafonov, Mohammad Yaqub, Maxim Panov, Martin Takáč
We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations.
1 code implementation • 5 Sep 2022 • Roman Kail, Kirill Fedyanin, Nikita Muravev, Alexey Zaytsev, Maxim Panov
The performance of modern deep learning-based systems dramatically depends on the quality of input objects.
no code implementations • 21 Jun 2022 • Gleb Bazhenov, Sergei Ivanov, Maxim Panov, Alexey Zaytsev, Evgeny Burnaev
The problem of out-of-distribution detection for graph classification is far from being solved.
no code implementations • 6 May 2022 • Alexander Fishkov, Maxim Panov
Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains.
no code implementations • 24 Feb 2022 • Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky
In this limit, we identify two ensemble regimes - independent and collective - depending on the architecture and initialization strategy of ensemble models.
1 code implementation • 7 Feb 2022 • Nikita Kotelevskii, Aleksandr Artemenkov, Kirill Fedyanin, Fedor Noskov, Alexander Fishkov, Artem Shelmanov, Artem Vazhentsev, Aleksandr Petiushko, Maxim Panov
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions.
2 code implementations • 30 Jun 2021 • Achille Thin, Nikita Kotelevskii, Arnaud Doucet, Alain Durmus, Eric Moulines, Maxim Panov
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO).
1 code implementation • EACL 2021 • Artem Shelmanov, Evgenii Tsymbalov, Dmitri Puzyrev, Kirill Fedyanin, Alexander Panchenko, Maxim Panov
In this work, we consider the problem of uncertainty estimation for Transformer-based models.
no code implementations • 31 Dec 2020 • Achille Thin, Nikita Kotelevskii, Christophe Andrieu, Alain Durmus, Eric Moulines, Maxim Panov
This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms.
no code implementations • 30 Sep 2020 • Ivan Sukharev, Valentina Shumovskaia, Kirill Fedyanin, Maxim Panov, Dmitry Berestnev
In this paper, we discuss how modern deep learning approaches can be applied to the credit scoring of bank clients.
1 code implementation • 6 Mar 2020 • 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-of-distribution or adversarially generated points.
no code implementations • 27 Feb 2020 • Achille Thin, Nikita Kotelevskii, Jean-Stanislas Denain, Leo Grinsztajn, Alain Durmus, Maxim Panov, Eric Moulines
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC).
1 code implementation • 30 Jan 2020 • 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-dimensional data.
no code implementations • 23 Jan 2020 • Valentina Shumovskaia, Kirill Fedyanin, Ivan Sukharev, Dmitry Berestnev, Maxim Panov
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.
1 code implementation • 12 Apr 2019 • Marina Gomtsyan, Nikita Mokrov, Maxim Panov, Yury Yanovich
The existing approaches to intrinsic dimension estimation usually are not reliable when the data are nonlinearly embedded in the high dimensional space.
1 code implementation • 27 Feb 2019 • Evgenii Tsymbalov, Sergei Makarychev, Alexander Shapeev, Maxim Panov
Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation.
no code implementations • 6 Oct 2018 • Stanislav Tsepa, Maxim Panov
The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science.
no code implementations • 26 Jun 2018 • Evgenii Tsymbalov, Maxim Panov, Alexander Shapeev
Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive.
no code implementations • 27 Apr 2018 • Ivan Nazarov, Boris Shirokikh, Maria Burkina, Gennady Fedonin, Maxim Panov
We consider the problem of matrix completion with side information (\textit{inductive matrix completion}).
no code implementations • 14 Oct 2017 • Nikita Mokrov, Maxim Panov, Boris A. Gutman, Joshua I. Faskowitz, Neda Jahanshad, Paul M. Thompson
This paper considers the problem of brain disease classification based on connectome data.
2 code implementations • 5 Jul 2017 • Maxim Panov, Konstantin Slavnov, Roman Ushakov
This paper considers the parameter estimation problem in Mixed Membership Stochastic Block Model (MMSB), which is a quite general instance of random graph model allowing for overlapping community structure.
Statistics Theory Statistics Theory
1 code implementation • 5 Sep 2016 • Mikhail Belyaev, Evgeny Burnaev, Ermek Kapushev, Maxim Panov, Pavel Prikhodko, Dmitry Vetrov, Dmitry Yarotsky
We describe GTApprox - a new tool for medium-scale surrogate modeling in industrial design.