Alert button
Picture for Ivan Nazarov

Ivan Nazarov

Alert button

Insights From the NeurIPS 2021 NetHack Challenge

Mar 22, 2022
Eric Hambro, Sharada Mohanty, Dmitrii Babaev, Minwoo Byeon, Dipam Chakraborty, Edward Grefenstette, Minqi Jiang, Daejin Jo, Anssi Kanervisto, Jongmin Kim, Sungwoong Kim, Robert Kirk, Vitaly Kurin, Heinrich Küttler, Taehwon Kwon, Donghoon Lee, Vegard Mella, Nantas Nardelli, Ivan Nazarov, Nikita Ovsov, Jack Parker-Holder, Roberta Raileanu, Karolis Ramanauskas, Tim Rocktäschel, Danielle Rothermel, Mikayel Samvelyan, Dmitry Sorokin, Maciej Sypetkowski, Michał Sypetkowski

Figure 1 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 2 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 3 for Insights From the NeurIPS 2021 NetHack Challenge
Figure 4 for Insights From the NeurIPS 2021 NetHack Challenge

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by interacting with the NetHack Learning Environment (NLE), a scalable, procedurally generated, and challenging Gym environment for reinforcement learning (RL). The challenge showcased community-driven progress in AI with many diverse approaches significantly beating the previously best results on NetHack. Furthermore, it served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems, demonstrating that on NetHack symbolic bots currently outperform deep RL by a large margin. Lastly, no agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.

* Under review at PMLR for the NeuRIPS 2021 Competition Workshop Track, 10 pages + 10 in appendices 
Viaarxiv icon

Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough

Jul 12, 2021
Alexander Ponomarchuk, Ilya Burenko, Elian Malkin, Ivan Nazarov, Vladimir Kokh, Manvel Avetisian, Leonid Zhukov

Figure 1 for Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough
Figure 2 for Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough
Figure 3 for Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough
Figure 4 for Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough

The COVID-19 pandemic created a significant interest and demand for infection detection and monitoring solutions. In this paper we propose a machine learning method to quickly triage COVID-19 using recordings made on consumer devices. The approach combines signal processing methods with fine-tuned deep learning networks and provides methods for signal denoising, cough detection and classification. We have also developed and deployed a mobile application that uses symptoms checker together with voice, breath and cough signals to detect COVID-19 infection. The application showed robust performance on both open sourced datasets and on the noisy data collected during beta testing by the end users.

Viaarxiv icon

Topology-based Clusterwise Regression for User Segmentation and Demand Forecasting

Sep 08, 2020
Rodrigo Rivera-Castro, Aleksandr Pletnev, Polina Pilyugina, Grecia Diaz, Ivan Nazarov, Wanyi Zhu, Evgeny Burnaev

Figure 1 for Topology-based Clusterwise Regression for User Segmentation and Demand Forecasting
Figure 2 for Topology-based Clusterwise Regression for User Segmentation and Demand Forecasting
Figure 3 for Topology-based Clusterwise Regression for User Segmentation and Demand Forecasting
Figure 4 for Topology-based Clusterwise Regression for User Segmentation and Demand Forecasting

Topological Data Analysis (TDA) is a recent approach to analyze data sets from the perspective of their topological structure. Its use for time series data has been limited. In this work, a system developed for a leading provider of cloud computing combining both user segmentation and demand forecasting is presented. It consists of a TDA-based clustering method for time series inspired by a popular managerial framework for customer segmentation and extended to the case of clusterwise regression using matrix factorization methods to forecast demand. Increasing customer loyalty and producing accurate forecasts remain active topics of discussion both for researchers and managers. Using a public and a novel proprietary data set of commercial data, this research shows that the proposed system enables analysts to both cluster their user base and plan demand at a granular level with significantly higher accuracy than a state of the art baseline. This work thus seeks to introduce TDA-based clustering of time series and clusterwise regression with matrix factorization methods as viable tools for the practitioner.

* 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA)  
Viaarxiv icon

Bayesian Sparsification Methods for Deep Complex-valued Networks

Mar 25, 2020
Ivan Nazarov, Evgeny Burnaev

Figure 1 for Bayesian Sparsification Methods for Deep Complex-valued Networks
Figure 2 for Bayesian Sparsification Methods for Deep Complex-valued Networks
Figure 3 for Bayesian Sparsification Methods for Deep Complex-valued Networks
Figure 4 for Bayesian Sparsification Methods for Deep Complex-valued Networks

With continual miniaturization ever more applications of deep learning can be found in embedded systems, where it is common to encounter data with natural complex domain representation. To this end we extend Sparse Variational Dropout to complex-valued neural networks and verify the proposed Bayesian technique by conducting a large numerical study of the performance-compression trade-off of C-valued networks on two tasks: image recognition on MNIST-like and CIFAR10 datasets and music transcription on MusicNet. We replicate the state-of-the-art result by Trabelsi et al. [2018] on MusicNet with a complex-valued network compressed by 50-100x at a small performance penalty.

Viaarxiv icon

Demand forecasting techniques for build-to-order lean manufacturing supply chains

May 20, 2019
Rodrigo Rivera-Castro, Ivan Nazarov, Yuke Xiang, Alexander Pletneev, Ivan Maksimov, Evgeny Burnaev

Figure 1 for Demand forecasting techniques for build-to-order lean manufacturing supply chains
Figure 2 for Demand forecasting techniques for build-to-order lean manufacturing supply chains

Build-to-order (BTO) supply chains have become common-place in industries such as electronics, automotive and fashion. They enable building products based on individual requirements with a short lead time and minimum inventory and production costs. Due to their nature, they differ significantly from traditional supply chains. However, there have not been studies dedicated to demand forecasting methods for this type of setting. This work makes two contributions. First, it presents a new and unique data set from a manufacturer in the BTO sector. Second, it proposes a novel data transformation technique for demand forecasting of BTO products. Results from thirteen forecasting methods show that the approach compares well to the state-of-the-art while being easy to implement and to explain to decision-makers.

* 16th International Symposium on Neural Networks, ISNN 2019  
* 10 pages, 2 figures 
Viaarxiv icon

Sparse Group Inductive Matrix Completion

Oct 06, 2018
Ivan Nazarov, Boris Shirokikh, Maria Burkina, Gennady Fedonin, Maxim Panov

Figure 1 for Sparse Group Inductive Matrix Completion
Figure 2 for Sparse Group Inductive Matrix Completion
Figure 3 for Sparse Group Inductive Matrix Completion
Figure 4 for Sparse Group Inductive Matrix Completion

We consider the problem of matrix completion with side information (\textit{inductive matrix completion}). In real-world applications many side-channel features are typically non-informative making feature selection an important part of the problem. We incorporate feature selection into inductive matrix completion by proposing a matrix factorization framework with group-lasso regularization on side feature parameter matrices. We demonstrate, that the theoretical sample complexity for the proposed method is much lower compared to its competitors in sparse problems, and propose an efficient optimization algorithm for the resulting low-rank matrix completion problem with sparsifying regularizers. Experiments on synthetic and real-world datasets show that the proposed approach outperforms other methods.

Viaarxiv icon

Conformal k-NN Anomaly Detector for Univariate Data Streams

Jun 11, 2017
Vladislav Ishimtsev, Ivan Nazarov, Alexander Bernstein, Evgeny Burnaev

Figure 1 for Conformal k-NN Anomaly Detector for Univariate Data Streams
Figure 2 for Conformal k-NN Anomaly Detector for Univariate Data Streams
Figure 3 for Conformal k-NN Anomaly Detector for Univariate Data Streams
Figure 4 for Conformal k-NN Anomaly Detector for Univariate Data Streams

Anomalies in time-series data give essential and often actionable information in many applications. In this paper we consider a model-free anomaly detection method for univariate time-series which adapts to non-stationarity in the data stream and provides probabilistic abnormality scores based on the conformal prediction paradigm. Despite its simplicity the method performs on par with complex prediction-based models on the Numenta Anomaly Detection benchmark and the Yahoo! S5 dataset.

* 15 pages, 2 figures, 7 tables 
Viaarxiv icon

Steganographic Generative Adversarial Networks

Mar 16, 2017
Denis Volkhonskiy, Ivan Nazarov, Boris Borisenko, Evgeny Burnaev

Figure 1 for Steganographic Generative Adversarial Networks
Figure 2 for Steganographic Generative Adversarial Networks
Figure 3 for Steganographic Generative Adversarial Networks
Figure 4 for Steganographic Generative Adversarial Networks

Steganography is collection of methods to hide secret information ("payload") within non-secret information ("container"). Its counterpart, Steganalysis, is the practice of determining if a message contains a hidden payload, and recovering it if possible. Presence of hidden payloads is typically detected by a binary classifier. In the present study, we propose a new model for generating image-like containers based on Deep Convolutional Generative Adversarial Networks (DCGAN). This approach allows to generate more setganalysis-secure message embedding using standard steganography algorithms. Experiment results demonstrate that the new model successfully deceives the steganography analyzer, and for this reason, can be used in steganographic applications.

* 8 pages, 2 figures, Workshop on Adversarial Training (NIPS 2016, Barcelona, Spain) 
Viaarxiv icon

Conformalized Kernel Ridge Regression

Sep 19, 2016
Evgeny Burnaev, Ivan Nazarov

Figure 1 for Conformalized Kernel Ridge Regression
Figure 2 for Conformalized Kernel Ridge Regression
Figure 3 for Conformalized Kernel Ridge Regression
Figure 4 for Conformalized Kernel Ridge Regression

General predictive models do not provide a measure of confidence in predictions without Bayesian assumptions. A way to circumvent potential restrictions is to use conformal methods for constructing non-parametric confidence regions, that offer guarantees regarding validity. In this paper we provide a detailed description of a computationally efficient conformal procedure for Kernel Ridge Regression (KRR), and conduct a comparative numerical study to see how well conformal regions perform against the Bayesian confidence sets. The results suggest that conformalized KRR can yield predictive confidence regions with specified coverage rate, which is essential in constructing anomaly detection systems based on predictive models.

* 8 pages, 8 figures, 4 tables 
Viaarxiv icon