arXiv subjects

Evgeny Burnaev

Publications and source records attributed to Evgeny Burnaev.

At least 127 records · Page 7Linked to original sources

arXiv2021

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we address this issue for quadratic-cost transport -- specifically, computation of the Wasserstein-2 distance, a commonly-used formulation of optimal transport in machine learning. To overcome the challenge of computing ground truth transport maps between continuous measures needed to assess these solvers, we use input-convex neural networks (ICNN) to construct pairs of measures whose ground truth OT maps can be obtained analytically. This strategy yields pairs of continuous benchmark measures in high-dimensional spaces such as spaces of images. We thoroughly evaluate existing optimal transport solvers using these benchmark measures. Even though these solvers perform well in downstream tasks, many do not faithfully recover optimal transport maps. To investigate the cause of this discrepancy, we further test the solvers in a setting of image generation. Our study reveals crucial limitations of existing solvers and shows that increased OT accuracy does not necessarily correlate to better results downstream.

cs.LG↗

arXiv2021

Development of Deep Transformer-Based Models for Long-Term Prediction of Transient Production of Oil Wells

We propose a novel approach to data-driven modeling of a transient production of oil wells. We apply the transformer-based neural networks trained on the multivariate time series composed of various parameters of oil wells measured during their exploitation. By tuning the machine learning models for a single well (ignoring the effect of neighboring wells) on the open-source field datasets, we demonstrate that transformer outperforms recurrent neural networks with LSTM/GRU cells in the forecasting of the bottomhole pressure dynamics. We apply the transfer learning procedure to the transformer-based surrogate model, which includes the initial training on the dataset from a certain well and additional tuning of the model's weights on the dataset from a target well. Transfer learning approach helps to improve the prediction capability of the model. Next, we generalize the single-well model based on the transformer architecture for multiple wells to simulate complex transient oilfield-level patterns. In other words, we create the global model which deals with the dataset, comprised of the production history from multiple wells, and allows for capturing the well interference resulting in more accurate prediction of the bottomhole pressure or flow rate evolutions for each well under consideration. The developed instruments for a single-well and oilfield-scale modelling can be used to optimize the production process by selecting the operating regime and submersible equipment to increase the hydrocarbon recovery. In addition, the models can be helpful to perform well-testing avoiding costly shut-in operations.

cs.LG↗

arXiv2021

Machine learning for recovery factor estimation of an oil reservoir: a tool for de-risking at a hydrocarbon asset evaluation

Well known oil recovery factor estimation techniques such as analogy, volumetric calculations, material balance, decline curve analysis, hydrodynamic simulations have certain limitations. Those techniques are time-consuming, require specific data and expert knowledge. Besides, though uncertainty estimation is highly desirable for this problem, the methods above do not include this by default. In this work, we present a data-driven technique for oil recovery factor estimation using reservoir parameters and representative statistics. We apply advanced machine learning methods to historical worldwide oilfields datasets (more than 2000 oil reservoirs). The data-driven model might be used as a general tool for rapid and completely objective estimation of the oil recovery factor. In addition, it includes the ability to work with partial input data and to estimate the prediction interval of the oil recovery factor. We perform the evaluation in terms of accuracy and prediction intervals coverage for several tree-based machine learning techniques in application to the following two cases: (1) using parameters only related to geometry, geology, transport, storage and fluid properties, (2) using an extended set of parameters including development and production data. For both cases model proved itself to be robust and reliable. We conclude that the proposed data-driven approach overcomes several limitations of the traditional methods and is suitable for rapid, reliable and objective estimation of oil recovery factor for hydrocarbon reservoir.

stat.AP↗

arXiv2021

Random Fourier Features based SLAM

This work is dedicated to simultaneous continuous-time trajectory estimation and mapping based on Gaussian Processes (GP). State-of-the-art GP-based models for Simultaneous Localization and Mapping (SLAM) are computationally efficient but can only be used with a restricted class of kernel functions. This paper provides the algorithm based on GP with Random Fourier Features (RFF) approximation for SLAM without any constraints. The advantages of RFF for continuous-time SLAM are that we can consider a broader class of kernels and, at the same time, maintain computational complexity at reasonably low level by operating in the Fourier space of features. The accuracy-speed trade-off can be controlled by the number of features. Our experimental results on synthetic and real-world benchmarks demonstrate the cases in which our approach provides better results compared to the current state-of-the-art.

cs.RO↗

arXiv2021

AI-enabled Prediction of eSports Player Performance Using the Data from Heterogeneous Sensors

The emerging progress of eSports lacks the tools for ensuring high-quality analytics and training in Pro and amateur eSports teams. We report on an Artificial Intelligence (AI) enabled solution for predicting the eSports player in-game performance using exclusively the data from sensors. For this reason, we collected the physiological, environmental, and the game chair data from Pro and amateur players. The player performance is assessed from the game logs in a multiplayer game for each moment of time using a recurrent neural network. We have investigated that attention mechanism improves the generalization of the network and provides the straightforward feature importance as well. The best model achieves ROC AUC score 0.73. The prediction of the performance of particular player is realized although his data are not utilized in the training set. The proposed solution has a number of promising applications for Pro eSports teams and amateur players, such as a learning tool or a performance monitoring system.

cs.HC↗

arXiv2021

Detecting Video Game Player Burnout with the Use of Sensor Data and Machine Learning

Current research in eSports lacks the tools for proper game practising and performance analytics. The majority of prior work relied only on in-game data for advising the players on how to perform better. However, in-game mechanics and trends are frequently changed by new patches limiting the lifespan of the models trained exclusively on the in-game logs. In this article, we propose the methods based on the sensor data analysis for predicting whether a player will win the future encounter. The sensor data were collected from 10 participants in 22 matches in League of Legends video game. We have trained machine learning models including Transformer and Gated Recurrent Unit to predict whether the player wins the encounter taking place after some fixed time in the future. For 10 seconds forecasting horizon Transformer neural network architecture achieves ROC AUC score 0.706. This model is further developed into the detector capable of predicting that a player will lose the encounter occurring in 10 seconds in 88.3% of cases with 73.5% accuracy. This might be used as a players' burnout or fatigue detector, advising players to retreat. We have also investigated which physiological features affect the chance to win or lose the next in-game encounter.

cs.IR↗

arXiv2021

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks

In this paper, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on graph convolutional networks (GCNs). Unlike previous learning-based mesh denoising methods that exploit hand-crafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces a graph representation followed by graph convolution operations in the dual space of triangles. We show such a graph representation naturally captures the geometry features while being lightweight for both training and inference. To facilitate effective feature learning, our network exploits both static and dynamic edge convolutions, which allow us to learn information from both the explicit mesh structure and potential implicit relations among unconnected neighbors. To better approximate an unknown noise function, we introduce a cascaded optimization paradigm to progressively regress the noise-free facet normals with multiple GCNs. GCN-Denoiser achieves the new state-of-the-art results in multiple noise datasets, including CAD models often containing sharp features and raw scan models with real noise captured from different devices. We also create a new dataset called PrintData containing 20 real scans with their corresponding ground-truth meshes for the research community. Our code and data are available in https://github.com/Jhonve/GCN-Denoiser.

cs.GR↗

arXiv2021

Reconstruction of 3D Porous Media From 2D Slices

In many branches of earth sciences, the problem of rock study on the micro-level arises. However, a significant number of representative samples is not always feasible. Thus the problem of the generation of samples with similar properties becomes actual. In this paper, we propose a novel deep learning architecture for three-dimensional porous media reconstruction from two-dimensional slices. We fit a distribution on all possible three-dimensional structures of a specific type based on the given dataset of samples. Then, given partial information (central slices), we recover the three-dimensional structure around such slices as the most probable one according to that constructed distribution. Technically, we implement this in the form of a deep neural network with encoder, generator and discriminator modules. Numerical experiments show that this method provides a good reconstruction in terms of Minkowski functionals.

cs.CV↗

arXiv2021

Data-driven model for hydraulic fracturing design optimization. Part II: Inverse problem

We describe a stacked model for predicting the cumulative fluid production for an oil well with a multistage-fracture completion based on a combination of Ridge Regression and CatBoost algorithms. The model is developed based on an extended digital field data base of reservoir, well and fracturing design parameters. The database now includes more than 5000 wells from 23 oilfields of Western Siberia (Russia), with 6687 fracturing operations in total. Starting with 387 parameters characterizing each well, including construction, reservoir properties, fracturing design features and production, we end up with 38 key parameters used as input features for each well in the model training process. The model demonstrates physically explainable dependencies plots of the target on the design parameters (number of stages, proppant mass, average and final proppant concentrations and fluid rate). We developed a set of methods including those based on the use of Euclidean distance and clustering techniques to perform similar (offset) wells search, which is useful for a field engineer to analyze earlier fracturing treatments on similar wells. These approaches are also adapted for obtaining the optimization parameters boundaries for the particular pilot well, as part of the field testing campaign of the methodology. An inverse problem (selecting an optimum set of fracturing design parameters to maximize production) is formulated as optimizing a high dimensional black box approximation function constrained by boundaries and solved with four different optimization methods: surrogate-based optimization, sequential least squares programming, particle swarm optimization and differential evolution. A recommendation system containing all the above methods is designed to advise a production stimulation engineer on an optimized fracturing design.

cs.LG↗

arXiv2021

A Differentiable Language Model Adversarial Attack on Text Classifiers

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial attack scenario: check if a small perturbation of an input can fool a model. Due to the discrete nature of textual data, gradient-based adversarial methods, widely used in computer vision, are not applicable per~se. The standard strategy to overcome this issue is to develop token-level transformations, which do not take the whole sentence into account. In this paper, we propose a new black-box sentence-level attack. Our method fine-tunes a pre-trained language model to generate adversarial examples. A proposed differentiable loss function depends on a substitute classifier score and an approximate edit distance computed via a deep learning model. We show that the proposed attack outperforms competitors on a diverse set of NLP problems for both computed metrics and human evaluation. Moreover, due to the usage of the fine-tuned language model, the generated adversarial examples are hard to detect, thus current models are not robust. Hence, it is difficult to defend from the proposed attack, which is not the case for other attacks.

cs.CL↗

arXiv2021

Adversarial Attacks on Deep Models for Financial Transaction Records

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their tremendous number of parameters and limited robustness. In particular, deep-learning models are vulnerable to adversarial attacks: a little change in the input harms the model's output. In this work, we examine adversarial attacks on transaction records data and defences from these attacks. The transaction records data have a different structure than the canonical NLP or time series data, as neighbouring records are less connected than words in sentences, and each record consists of both discrete merchant code and continuous transaction amount. We consider a black-box attack scenario, where the attack doesn't know the true decision model, and pay special attention to adding transaction tokens to the end of a sequence. These limitations provide more realistic scenario, previously unexplored in NLP world. The proposed adversarial attacks and the respective defences demonstrate remarkable performance using relevant datasets from the financial industry. Our results show that a couple of generated transactions are sufficient to fool a deep-learning model. Further, we improve model robustness via adversarial training or separate adversarial examples detection. This work shows that embedding protection from adversarial attacks improves model robustness, allowing a wider adoption of deep models for transaction records in banking and finance.

cs.LG↗

arXiv2021

COHORTNEY: Non-Parametric Clustering of Event Sequences

Cohort analysis is a pervasive activity in web analytics. One divides users into groups according to specific criteria and tracks their behavior over time. Despite its extensive use, academic circles do not discuss cohort analysis to evaluate user behavior online. This work introduces an unsupervised non-parametric approach to group Internet users based on their activities. In comparison, canonical methods in marketing and engineering-based techniques underperform. COHORTNEY is the first machine learning-based cohort analysis algorithm with a robust theoretical explanation.

cs.LG↗

arXiv2021

Multi-fidelity Neural Architecture Search with Knowledge Distillation

Neural architecture search (NAS) targets at finding the optimal architecture of a neural network for a problem or a family of problems. Evaluations of neural architectures are very time-consuming. One of the possible ways to mitigate this issue is to use low-fidelity evaluations, namely training on a part of a dataset, fewer epochs, with fewer channels, etc. In this paper, we propose a bayesian multi-fidelity method for neural architecture search: MF-KD. The method relies on a new approach to low-fidelity evaluations of neural architectures by training for a few epochs using a knowledge distillation. Knowledge distillation adds to a loss function a term forcing a network to mimic some teacher network. We carry out experiments on CIFAR-10, CIFAR-100, and ImageNet-16-120. We show that training for a few epochs with such a modified loss function leads to a better selection of neural architectures than training for a few epochs with a logistic loss. The proposed method outperforms several state-of-the-art baselines.

cs.LG↗

arXiv2021

Inversion formula for infinitely divisible distributions

The aim of this note is to prove the inversion formula, which can be used to compute the Levi measure of an infinitely divisible distribution from its characteristic function. Obtained formula is similar to the well-known inversion formula [2], which is used to compute the distribution function of a random variable from the corresponding characteristic function.

math.PR↗

arXiv2021

Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization

Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport. In this paper, we present a scalable algorithm to compute Wasserstein-2 barycenters given sample access to the input measures, which are not restricted to being discrete. While past approaches rely on entropic or quadratic regularization, we employ input convex neural networks and cycle-consistency regularization to avoid introducing bias. As a result, our approach does not resort to minimax optimization. We provide theoretical analysis on error bounds as well as empirical evidence of the effectiveness of the proposed approach in low-dimensional qualitative scenarios and high-dimensional quantitative experiments.

cs.LG↗

arXiv2021

Denoising Score Matching with Random Fourier Features

The density estimation is one of the core problems in statistics. Despite this, existing techniques like maximum likelihood estimation are computationally inefficient due to the intractability of the normalizing constant. For this reason an interest to score matching has increased being independent on the normalizing constant. However, such estimator is consistent only for distributions with the full space support. One of the approaches to make it consistent is to add noise to the input data which is called Denoising Score Matching. In this work we derive analytical expression for the Denoising Score matching using the Kernel Exponential Family as a model distribution. The usage of the kernel exponential family is motivated by the richness of this class of densities. To tackle the computational complexity we use Random Fourier Features based approximation of the kernel function. The analytical expression allows to drop additional regularization terms based on the higher-order derivatives as they are already implicitly included. Moreover, the obtained expression explicitly depends on the noise variance, so the validation loss can be straightforwardly used to tune the noise level. Along with benchmark experiments, the model was tested on various synthetic distributions to study the behaviour of the model in different cases. The empirical study shows comparable quality to the competing approaches, while the proposed method being computationally faster. The latter one enables scaling up to complex high-dimensional data.

cs.LG↗

arXiv2020

Reinforcement Learning for Combinatorial Optimization: A Survey

Many traditional algorithms for solving combinatorial optimization problems involve using hand-crafted heuristics that sequentially construct a solution. Such heuristics are designed by domain experts and may often be suboptimal due to the hard nature of the problems. Reinforcement learning (RL) proposes a good alternative to automate the search of these heuristics by training an agent in a supervised or self-supervised manner. In this survey, we explore the recent advancements of applying RL frameworks to hard combinatorial problems. Our survey provides the necessary background for operations research and machine learning communities and showcases the works that are moving the field forward. We juxtapose recently proposed RL methods, laying out the timeline of the improvements for each problem, as well as we make a comparison with traditional algorithms, indicating that RL models can become a promising direction for solving combinatorial problems.

cs.LG↗

arXiv2020

Relightable 3D Head Portraits from a Smartphone Video

In this work, a system for creating a relightable 3D portrait of a human head is presented. Our neural pipeline operates on a sequence of frames captured by a smartphone camera with the flash blinking (flash-no flash sequence). A coarse point cloud reconstructed via structure-from-motion software and multi-view denoising is then used as a geometric proxy. Afterwards, a deep rendering network is trained to regress dense albedo, normals, and environmental lighting maps for arbitrary new viewpoints. Effectively, the proxy geometry and the rendering network constitute a relightable 3D portrait model, that can be synthesized from an arbitrary viewpoint and under arbitrary lighting, e.g. directional light, point light, or an environment map. The model is fitted to the sequence of frames with human face-specific priors that enforce the plausibility of albedo-lighting decomposition and operates at the interactive frame rate. We evaluate the performance of the method under varying lighting conditions and at the extrapolated viewpoints and compare with existing relighting methods.

cs.CV↗