George Ovchinnikov

Alexandr Katrutsa, Mike Botchev, George Ovchinnikov et al.

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.

Filipp Skomorokhov, George Ovchinnikov

This paper is dedicated to the application of reinforcement learning combined with neural networks to the general formulation of user scheduling problem. Our simulator resembles real world problems by means of stochastic changes in environment. We applied Q-learning based method to the number of dynamic simulations and outperformed analytical greedy-based solution in terms of total reward, the aim of which is to get the lowest possible penalty throughout simulation.

Artem Chashchin, Mikhail Botchev, Ivan Oseledets et al.

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.

Artem L. Pavlov, Azat Davletshin, Alexey Kharlamov et al.

With the advancements of various autonomous car projects aiming to achieve SAE Level 5, real-time detection of traffic signs in real-life scenarios has become a highly relevant problem for the industry. Even though a great progress has been achieved in this field, there is still no clear consensus on what the state-of-the-art in this field is. Moreover, it is important to develop and test systems in various regions and conditions. This is why the "Ice Vision" competition has focused on the detection of Russian traffic signs in winter conditions. The IceVisionSet dataset used for this competition features real-world collection of lossless frame sequences with traffic sign annotations. The sequences were collected in varying conditions, including: different weather, camera exposure, illumination and moving speeds. In this work we describe the competition and present the solutions of the 3 top teams.

A. L. Pavlov, G. V. Ovchinnikov, D. Yu. Derbyshev et al.

Iterative Closest Point (ICP) is a widely used method for performing scan-matching and registration. Being simple and robust method, it is still computationally expensive and may be challenging to use in real-time applications with limited resources on mobile platforms. In this paper we propose novel effective method for acceleration of ICP which does not require substantial modifications to the existing code. This method is based on an idea of Anderson acceleration which is an iterative procedure for finding a fixed point of contractive mapping. The latter is often faster than a standard Picard iteration, usually used in ICP implementations. We show that ICP, being a fixed point problem, can be significantly accelerated by this method enhanced by heuristics to improve overall robustness. We implement proposed approach into Point Cloud Library (PCL) and make it available online. Benchmarking on real-world data fully supports our claims.

G. V. Ovchinnikov, D. Zorin, I. V. Oseledets

Topological optimization finds a material density distribution minimizing a functional of the solution of a partial differential equation (PDE), subject to a set of constraints (typically, a bound on the volume or mass of the material). Using a finite elements discretization (FEM) of the PDE and functional we obtain an integer programming problem. Due to approximation error of FEM discretization, optimization problem becomes mesh-depended and possess false, physically inadequate optimums, while functional value heavily depends on fineness of discretization scheme used to compute it. To alleviate this problem, we propose regularization of given functional by error estimate of FEM discretization. This regularization provides robustness of solutions and improves obtained functional values as well. While the idea is broadly applicable, in this paper we apply our method to the heat conduction optimization. This type of problems are of practical importance in design of heat conduction channels, heat sinks and other types of heat guides.