arXiv subjects

Ivan Oseledets

Publications and source records attributed to Ivan Oseledets.

At least 199 records · Page 11Linked to original sources

arXiv2020

Deep Representation Learning for Dynamical Systems Modeling

Proper states' representations are the key to the successful dynamics modeling of chaotic systems. Inspired by recent advances of deep representations in various areas such as natural language processing and computer vision, we propose the adaptation of the state-of-art Transformer model in application to the dynamical systems modeling. The model demonstrates promising results in trajectories generation as well as in the general attractors' characteristics approximation, including states' distribution and Lyapunov exponent.

math.DS↗

arXiv2019

An adaptive algorithm for quantum circuit simulation

Efficient simulation of quantum computers is essential for the development and validation of near-term quantum devices and the research on quantum algorithms. Up to date, two main approaches to simulation were in use, based on either full state or single amplitude evaluation. We propose an algorithm that efficiently interpolates between these two possibilities. Our approach elucidates the connection between quantum circuit simulation and partial evaluation of expressions in tensor algebra.

cs.CC↗

arXiv2019

MUSCO: Multi-Stage Compression of neural networks

The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.

cs.LG↗

arXiv2019

Predicting dynamical system evolution with residual neural networks

Forecasting time series and time-dependent data is a common problem in many applications. One typical example is solving ordinary differential equation (ODE) systems $\dot{x}=F(x)$. Oftentimes the right hand side function $F(x)$ is not known explicitly and the ODE system is described by solution samples taken at some time points. Hence, ODE solvers cannot be used. In this paper, a data-driven approach to learning the evolution of dynamical systems is considered. We show how by training neural networks with ResNet-like architecture on the solution samples, models can be developed to predict the ODE system solution further in time. By evaluating the proposed approaches on three test ODE systems, we demonstrate that the neural network models are able to reproduce the main dynamics of the systems qualitatively well. Moreover, the predicted solution remains stable for much longer times than for other currently known models.

physics.comp-ph↗

arXiv2019

Practical shift choice in the shift-and-invert Krylov subspace evaluations of the matrix exponential

We propose two methods to find a proper shift parameter in the shift-and-invert method for computing matrix exponential matrix-vector products. These methods are useful in the case of matrix exponential action has to be computed for a number of vectors. The first method is based on the zero-order optimization of the mean residual norm for a given number of initial vectors. The second method processes the vectors one-by-one and estimates, for each vector, the derivative of the residual norm as a function of the shift parameter. The estimated derivative value is then used to update the shift value for the next vector. To demonstrate the performance of the proposed methods we perform numerical experiments for two-dimensional non-stationary convection-diffusion equation with discontinuous coefficients and two-dimensional anisotropic diffusion equation.

math.NA↗

arXiv2019

Microstructure synthesis using style-based generative adversarial network

Work considers the usage of StyleGAN architecture for the task of microstructure synthesis. The task is the following: given number of samples of structure we try to generate similar samples at the same time preserving its properties. Since the considered architecture is not able to produce samples of sizes larger than the training images, we propose to use image quilting to merge fixed-sized samples. One of the key features of the considered architecture is that it uses multiple image resolutions. We also investigate the necessity of such an approach.

eess.IV↗

arXiv2019

HybridSVD: When Collaborative Information is Not Enough

We propose a new hybrid algorithm that allows incorporating both user and item side information within the standard collaborative filtering technique. One of its key features is that it naturally extends a simple PureSVD approach and inherits its unique advantages, such as highly efficient Lanczos-based optimization procedure, simplified hyper-parameter tuning and a quick folding-in computation for generating recommendations instantly even in highly dynamic online environments. The algorithm utilizes a generalized formulation of the singular value decomposition, which adds flexibility to the solution and allows imposing the desired structure on its latent space. Conveniently, the resulting model also admits an efficient and straightforward solution for the cold start scenario. We evaluate our approach on a diverse set of datasets and show its superiority over similar classes of hybrid models.

cs.LG↗

arXiv2019

Empirical study of extreme overfitting points of neural networks

In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, simultaneously with almost zero accuracy on the test sample. Despite the widespread opinion that the overwhelming majority of critical points of the loss function of a neural network have equally good generalizing ability, such points have a huge generalization error. The paper studies the properties of such points and their location on the surface of the loss function of modern neural networks.

cs.LG↗

arXiv2019

Deep Neural Networks Predicting Oil Movement in a Development Unit

We present a novel technique for assessing the dynamics of multiphase fluid flow in the oil reservoir. We demonstrate an efficient workflow for handling the 3D reservoir simulation data in a way which is orders of magnitude faster than the conventional routine. The workflow (we call it "Metamodel") is based on a projection of the system dynamics into a latent variable space, using Variational Autoencoder model, where Recurrent Neural Network predicts the dynamics. We show that being trained on multiple results of the conventional reservoir modelling, the Metamodel does not compromise the accuracy of the reservoir dynamics reconstruction in a significant way. It allows forecasting not only the flow rates from the wells, but also the dynamics of pressure and fluid saturations within the reservoir. The results open a new perspective in the optimization of oilfield development as the scenario screening could be accelerated sufficiently.

cs.LG↗

arXiv2019

How to optimize preconditioners for the conjugate gradient method: a stochastic approach

The conjugate gradient method (CG) is typically used with a preconditioner which improves efficiency and robustness of the method. Many preconditioners include parameters and a proper choice of a preconditioner and its parameters is often not a trivial task. Although many convergence estimates exist which can be used for optimizing preconditioners, these estimates typically hold for all initial guess vectors, in other words, they reflect the worst convergence rate. To account for the mean convergence rate instead, in this paper, we follow a stochastic approach. It is based on trial runs with random initial guess vectors and leads to a functional which can be used to monitor convergence and to optimize preconditioner parameters in CG. Presented numerical experiments show that optimization of this new functional with respect to preconditioner parameters usually yields a better parameter value than optimization of the functional based on the spectral condition number.

math.NA↗

arXiv2019

Preconditioning Kaczmarz method by sketching

We propose a new method for preconditioning Kaczmarz method by sketching. Kaczmarz method is a stochastic method for solving overdetermined linear systems based on a sampling of matrix rows. The standard approach to speed up convergence of iterative methods is using preconditioner. As we show the best possible preconditioner for this method can be constructed from QR decomposition of the system matrix, but the complexity of this procedure is too high. Therefore, to reduce this complexity, we use random sketching and compare it with the Kaczmarz method without preconditioning. The developed method is applicable for different modifications of classical Kaczmarz method that were proposed recently. We provide numerical experiments to show the performance of the developed methods on solving both random and real overdetermined linear systems.

math.NA↗

arXiv2019

Generalized Tensor Models for Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs enjoys the property of depth efficiency --- a shallow network of exponentially large width is necessary to realize the same score function as computed by such an RNN. Such networks, however, are not very often applied to real life tasks. In this work, we attempt to reduce the gap between theory and practice by extending the theoretical analysis to RNNs which employ various nonlinearities, such as Rectified Linear Unit (ReLU), and show that they also benefit from properties of universality and depth efficiency. Our theoretical results are verified by a series of extensive computational experiments.

cs.LG↗

arXiv2019

Alternating least squares as moving subspace correction

In this note we take a new look at the local convergence of alternating optimization methods for low-rank matrices and tensors. Our abstract interpretation as sequential optimization on moving subspaces yields insightful reformulations of some known convergence conditions that focus on the interplay between the contractivity of classical multiplicative Schwarz methods with overlapping subspaces and the curvature of low-rank matrix and tensor manifolds. While the verification of the abstract conditions in concrete scenarios remains open in most cases, we are able to provide an alternative and conceptually simple derivation of the asymptotic convergence rate of the two-sided block power method of numerical algebra for computing the dominant singular subspaces of a rectangular matrix. This method is equivalent to an alternating least squares method applied to a distance function. The theoretical results are illustrated and validated by numerical experiments.

math.NA↗

arXiv2019

PROVEN: Certifying Robustness of Neural Networks with a Probabilistic Approach

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature merely focuses on the \textit{worst-case} setting where the input of the neural network is perturbed with noises that are constrained within an $\ell_p$ ball; and several algorithms have been proposed to compute certified lower bounds of minimum adversarial distortion based on such worst-case analysis. In this paper, we address these limitations and extend the approach to a \textit{probabilistic} setting where the additive noises can follow a given distributional characterization. We propose a novel probabilistic framework PROVEN to PRObabilistically VErify Neural networks with statistical guarantees -- i.e., PROVEN certifies the probability that the classifier's top-1 prediction cannot be altered under any constrained $\ell_p$ norm perturbation to a given input. Importantly, we show that it is possible to derive closed-form probabilistic certificates based on current state-of-the-art neural network robustness verification frameworks. Hence, the probabilistic certificates provided by PROVEN come naturally and with almost no overhead when obtaining the worst-case certified lower bounds from existing methods such as Fast-Lin, CROWN and CNN-Cert. Experiments on small and large MNIST and CIFAR neural network models demonstrate our probabilistic approach can achieve up to around $75\%$ improvement in the robustness certification with at least a $99.99\%$ confidence compared with the worst-case robustness certificate delivered by CROWN.

cs.LG↗

arXiv2018

Low-rank Riemannian eigensolver for high-dimensional Hamiltonians

Such problems as computation of spectra of spin chains and vibrational spectra of molecules can be written as high-dimensional eigenvalue problems, i.e., when the eigenvector can be naturally represented as a multidimensional tensor. Tensor methods have proven to be an efficient tool for the approximation of solutions of high-dimensional eigenvalue problems, however, their performance deteriorates quickly when the number of eigenstates to be computed increases. We address this issue by designing a new algorithm motivated by the ideas of Riemannian optimization (optimization on smooth manifolds) for the approximation of multiple eigenstates in the tensor-train format, which is also known as matrix product state representation. The proposed algorithm is implemented in TensorFlow, which allows for both CPU and GPU parallelization.

math.NA↗

arXiv2018

Adversarial point set registration

We present a novel approach to point set registration which is based on one-shot adversarial learning. The idea of the algorithm is inspired by recent successes of generative adversarial networks. Treating the point clouds as three-dimensional probability distributions, we develop a one-shot adversarial optimization procedure, in which we train a critic neural network to distinguish between source and target point sets, while simultaneously learning the parameters of the transformation to trick the critic into confusing the points. In contrast to most existing algorithms for point set registration, ours does not rely on any correspondences between the point clouds. We demonstrate the performance of the algorithm on several challenging benchmarks and compare it to the existing baselines.

cs.CV↗

arXiv2018

Quadrature-based features for kernel approximation

We consider the problem of improving kernel approximation via randomized feature maps. These maps arise as Monte Carlo approximation to integral representations of kernel functions and scale up kernel methods for larger datasets. Based on an efficient numerical integration technique, we propose a unifying approach that reinterprets the previous random features methods and extends to better estimates of the kernel approximation. We derive the convergence behaviour and conduct an extensive empirical study that supports our hypothesis.

cs.LG↗

arXiv2018

Tensor Networks for Latent Variable Analysis: Higher Order Canonical Polyadic Decomposition

The Canonical Polyadic decomposition (CPD) is a convenient and intuitive tool for tensor factorization; however, for higher-order tensors, it often exhibits high computational cost and permutation of tensor entries, these undesirable effects grow exponentially with the tensor order. Prior compression of tensor in-hand can reduce the computational cost of CPD, but this is only applicable when the rank $R$ of the decomposition does not exceed the tensor dimensions. To resolve these issues, we present a novel method for CPD of higher-order tensors, which rests upon a simple tensor network of representative inter-connected core tensors of orders not higher than 3. For rigour, we develop an exact conversion scheme from the core tensors to the factor matrices in CPD, and an iterative algorithm with low complexity to estimate these factor matrices for the inexact case. Comprehensive simulations over a variety of scenarios support the approach.

math.NA↗