arXiv subjects

George Ovchinnikov

Publications and source records attributed to George Ovchinnikov.

7 recordsLinked to original sources

arXiv2026

Trade-Size-Aware Dynamic Fees for Impermanent Loss Mitigation in AMMs

Automated Market Makers enable decentralized trading but systematically expose liquidity providers to impermanent loss through arbitrage-driven rebalancing. While dynamic fee mechanisms offer a promising mitigation strategy, existing approaches remain largely reactive, adjusting costs based on historical signals rather than explicitly linking them to the structural risk imposed by individual trades. To address this limitation, we propose a novel fee formation framework built on three core innovations. First, we introduce a coupled market maker architecture in which fee dynamics are governed by a secondary invariant, allowing liquidity state and transaction costs to evolve jointly. Second, we develop an impermanent-loss trimming fee model that adaptively increases transaction costs for trades exceeding the liquidity providers' profitable region, effectively offsetting losses from large arbitrage executions while preserving baseline fees for smaller transactions. Third, we establish a unified evaluation methodology using performance profiles to systematically compare fee algorithms across diverse market conditions. By extending a heterogeneous trader model to derive optimal arbitrage strategies under state-dependent fees, we conduct extensive simulations on historical data spanning four distinct market regimes and three token pair categories. Our results demonstrate that the proposed fee enhancements improve liquidity provider yields by 6--24% in volatile markets and up to 119% in calm regimes, while maintaining uninformed user participation and reducing informed arbitrage profitability by 3--10%. Performance profile analysis confirms that ILT-enhanced algorithms dominate baseline counterparts across 60--75% of test scenarios.

cs.CE↗

arXiv2025

Dynamic Fee for Reducing Impermanent Loss in Decentralized Exchanges

Decentralized exchanges (DEXs) are crucial to decentralized finance (DeFi) as they enable trading without intermediaries. However, they face challenges like impermanent loss (IL), where liquidity providers (LPs) see their assets' value change unfavorably within a liquidity pool compared to outside it. To tackle these issues, we propose dynamic fee mechanisms over traditional fixed-fee structures used in automated market makers (AMM). Our solution includes asymmetric fees via block-adaptive, deal-adaptive, and the "ideal but unattainable" oracle-based fee algorithm, utilizing all data available to arbitrageurs to mitigate IL. We developed a simulation-based framework to compare these fee algorithms systematically. This framework replicates trading on a DEX, considering both informed and uninformed users and a psychological relative loss factor. Results show that adaptive algorithms outperform fixed-fee baselines in reducing IL while maintaining trading activity among uninformed users. Additionally, insights from oracle-based performance underscore the potential of dynamic fee strategies to lower IL, boost LP profitability, and enhance overall market efficiency.

cs.GT↗

arXiv2020

Reinforcement Learning for Assignment problem

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.

cs.AI↗

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

A parameteric class of composites with a large achievable range of effective elastic properties

In this paper we investigate numerically an instance of the problem of G-closure for two-dimensional periodic metamaterials. Specifically, we consider composites with isotropic homogenized elasticity tensor, obtained as a mixture of two isotropic materials, focusing on the case of a single material with voids. This problem is important, in particular, in the context of designing small-scale structures for metamaterials in the context of additive fabrication, as this type of metamaterials makes it possible to obtain a range of material properties using a single base material. We demonstrate that two closely related simple parametric families based on the structure proposed by O. Sigmund attain good coverage of the space of isotropic properties satisfying Hashin-Shtrikman bounds. In particular, for positive Poisson ratio, we demonstrate that Hashin-Shtrikman bound can be approximated arbitrarily well, within limits imposed by numerical approximation: a strong evidence that these bounds are achievable in this case. For negative Poisson ratios, we numerically obtain a bound which we hypothesize to be close to optimal, at least for metamaterials with rotational symmetries of a regular triangle tiling.

physics.comp-ph↗

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

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↗