Doklady Mathematics最新文献_第4页

Erratum to: JDCEMB: Joint Distillation and Contrastive Learning for Embeddings in Task-Oriented Dialogue Systems JDCEMB：任务导向对话系统中嵌入的联合蒸馏和对比学习

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425330014

A. I. Burykina, D. R. Ledneva, D. P. Kuznetsov

引用次数: 0

Dynamic Division of Labor in Hybrid AI: Contrasting Encoder Strategies and Their Impact on LSTM Modulators 混合人工智能中的动态分工：编码器策略对比及其对LSTM调制器的影响

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700590

A. K. Zvereva, A. V. Grabovoy, M. S. Kaprielova

{"title":"Dynamic Division of Labor in Hybrid AI: Contrasting Encoder Strategies and Their Impact on LSTM Modulators","authors":"A. K. Zvereva, A. V. Grabovoy, M. S. Kaprielova","doi":"10.1134/S1064562425700590","DOIUrl":"10.1134/S1064562425700590","url":null,"abstract":"The collaboration between spatial encoders, such as CNNs and Vision Transformers (ViTs), and temporal modulators like LSTMs is fundamental to hybrid models, yet the dynamics of this interplay remain poorly understood. This study introduces a cross-domain framework, leveraging metrics from Information Theory and the Markov Information Bottleneck (MIB) principle, to quantify the internal information flows of these architectures. We analyze two distinct models—a CNN-LSTM for surveillance video and a ViT-LSTM for medical fMRI sequences—on both their native and foreign domains. Our analysis reveals two fundamentally different encoding strategies. The CNN employs a rigid, data-agnostic ‘Gradual Compression’ pipeline. The ViT, in contrast, demonstrates an ‘Adaptive Compression’ strategy, where the successful formation of an efficient information bottleneck is conditional on the data domain. We demonstrate that this adaptability is supported by a nuanced three-stage functional hierarchy within the ViT. Furthermore, we find the LSTM modulator’s role adapts to its partner: paired with the CNN, it acts as a conventional compressor, but when paired with the ViT, it switches to an ‘unpacker’ role to process the hyper-compressed representations it receives. We propose that this complex interplay exemplifies a principle of a ‘Dynamic Division of Labor,’ where functional roles are not fixed but emerge from the system’s interaction with the data. This insight challenges the static view of neural network components and opens a path toward more robust, context-aware AI.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"541 - 552"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562425700590.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards Neural Multi View 3D Reconstruction from RGB-D Data 基于RGB-D数据的神经网络多视图三维重建

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700619

G. Bobrovskikh, O. Voynov, E. Burnaev

{"title":"Towards Neural Multi View 3D Reconstruction from RGB-D Data","authors":"G. Bobrovskikh, O. Voynov, E. Burnaev","doi":"10.1134/S1064562425700619","DOIUrl":"10.1134/S1064562425700619","url":null,"abstract":"Multi-view stereo (MVS) networks have recently achieved remarkable progress in dense 3D reconstruction, yet they remain fundamentally limited by reliance on photometric cues. As a result, current methods fail in textureless, reflective, or non-Lambertian regions. At the same time, commodity time-of-flight (ToF) sensors provide geometric depth information that is complementary but low-resolution and noisy. In this work study a possibility to use 3D features extracted from depth data to overcome MVS limitations. For this we develop RGB-D MVSNet, an end-to-end architecture that integrates a depth-fusion encoder with a modern learning-based MVS backbone. Our method constructs a unified feature volume from both photometric and geometric features, which is then fused and regularized in a with common decoder. We evaluate the approach on the challenging Sk3D dataset containing synchronized RGB, ToF depth, and high-quality structured-light scans. Experiments demonstrate that our method improves accuracy and completeness metrics over the RGB-only baseline and achieves some qualitative improvements in reconstructing textureless and glossy regions. Additional experiments with high-quality depth input show that the method is capable of eliminating typical artifacts with better input depth quality. These results indicate that integrating geometric cues into MVS pipelines is a promising direction towards more robust, generalizable 3D reconstruction.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"518 - 526"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Loss Barcode: A Topological Measure of Escapability in Loss Landscapes 损失条形码：损失景观中可逃避性的拓扑度量

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S106456242570053X

S. A. Barannikov, D. S. Voronkova, A. Mironenko, I. Trofimov, A. Korotin, G. Sotnikov, E. V. Burnaev

{"title":"Loss Barcode: A Topological Measure of Escapability in Loss Landscapes","authors":"S. A. Barannikov, D. S. Voronkova, A. Mironenko, I. Trofimov, A. Korotin, G. Sotnikov, E. V. Burnaev","doi":"10.1134/S106456242570053X","DOIUrl":"10.1134/S106456242570053X","url":null,"abstract":"Neural network training is commonly based on SGD. However, the understanding of SGD’s ability to converge to good local minima, given the non-convex nature of loss functions and the intricate geometric characteristics of loss landscapes, remains limited. In this paper, we apply topological data analysis methods to loss landscapes to gain insights into the learning process and generalization properties of deep neural networks. We use the loss function topology to relate the local behavior of gradient descent trajectories with the global properties of the loss surface. For this purpose, we define the neural networks Topological Obstructions score (“TO-score”) with the help of robust topological invariants, barcodes of the loss function, which quantify the escapability of local minima for gradient-based optimization. Our two principal observations are: (1) the loss barcode of the neural network decreases with increasing depth and width, therefore the topological obstructions to learning diminish; (2) in certain situations there is a connection between the length of minima segments in the loss barcode and the minima generalization errors. Our statements are based on extensive experiments with fully connected, convolutional, and transformer architectures and several datasets including MNIST, FMNIST, CIFAR10, CIFAR100, SVHN, and multilingual OSCAR text dataset.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"600 - 623"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S106456242570053X.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Erratum to: FoCAT: Foundation Model for Estimating the Conditional Average Treatment Effect 对FoCAT的勘误：估计条件平均处理效果的基础模型

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S106456242533004X

S. R. Kirpichenko, A. V. Konstantinov, L. V. Utkin

引用次数: 0

Cluster Validity across Attribute and Network Spaces: Empirical Benchmarks for Attributed Networks Clustering 跨属性和网络空间的聚类有效性：属性网络聚类的经验基准

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700589

S. Shalileh, E. A. Antonov, D. A. Tsyplakova

{"title":"Cluster Validity across Attribute and Network Spaces: Empirical Benchmarks for Attributed Networks Clustering","authors":"S. Shalileh, E. A. Antonov, D. A. Tsyplakova","doi":"10.1134/S1064562425700589","DOIUrl":"10.1134/S1064562425700589","url":null,"abstract":"We empirically study internal cluster validity indices for attributed networks by evaluating feature- and network-space criteria under controlled generators that decouple attributes from topology while sharing cluster cardinalities. Using unified notation, Gaussian blobs for features, and a stochastic block model for graphs, we assess Silhouette Width (SW), Calinski–Harabasz (CH), Davies–Bouldin (DBI), ({{S}_{{{text{Dbw}}}}}), Average Isolability (AVI), Average Unifiability (AVU), and ANUI on both ground-truth and random partitions. SW is stable and saturates once enough features are present; CH grows strongly with sample size (suggesting reporting CH/N); DBI and ({{S}_{{{text{Dbw}}}}}) separate ground truth from random partitions but have K-dependent random baselines, motivating baseline normalization. In network space, AVI increases with assortativity and decreases roughly as 1/K, AVU drops with K toward a floor, and ANUI follows these trends; all indices approach random baselines as overlap/mixing increases, while confidence intervals narrow with more samples or informative features. We provide an empirical benchmark, simple scaling heuristics, and practical guidance for applying CVIs in attributed networks.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"553 - 564"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562425700589.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating the Effectiveness of Large Language Models in Identifying Communicatively Significant Errors in Papers of Students Learning Russian as a Foreign Language 评价大型语言模型在识别对外俄语学习论文中交际性重大错误中的有效性

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700577

V. A. Shulginov, K. S. Klokova, T. A. Yudina, T. M. Obukhova, M. Yu. Lebedeva

{"title":"Evaluating the Effectiveness of Large Language Models in Identifying Communicatively Significant Errors in Papers of Students Learning Russian as a Foreign Language","authors":"V. A. Shulginov, K. S. Klokova, T. A. Yudina, T. M. Obukhova, M. Yu. Lebedeva","doi":"10.1134/S1064562425700577","DOIUrl":"10.1134/S1064562425700577","url":null,"abstract":"This paper examines the capability of contemporary large language models (LLMs), such as GPT-5 and DeepSeek-R1, to identify and classify communicative errors in papers of students learning Russian as a foreign language (RFL). While existing tools primarily focus on formal errors, this study emphasizes the communicative aspect, evaluating the extent to which an error disrupts comprehension (i.e., communicatively significant errors) or merely affects linguistic norms (i.e., communicatively insignificant errors). To this end, a corpus of papers by B2-level students (TORFL-2) was created and annotated by experts, and a multi-stage pipeline for testing LLMs was developed, incorporating structured prompting and heuristic voting methods to enhance result reliability. The experiment revealed that while models can localize errors with certain accuracy, they experience considerable difficulties in their proper communicative classification. The models tend to systematically underestimate the degree of error impact on comprehension, confuse error types, and encounter challenges in identifying multiple errors within a single fragment. The study demonstrates both the potential and current limitations of LLMs as tools for automated, communicatively oriented feedback in educational technologies.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"565 - 571"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Re:Frame—Retrieving Experience from Associative Memory Re：联想记忆中的帧检索经验

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700632

D. V. Zelezetsky, E. K. Cherepanov, A. K. Kovalev, A. I. Panov

{"title":"Re:Frame—Retrieving Experience from Associative Memory","authors":"D. V. Zelezetsky, E. K. Cherepanov, A. K. Kovalev, A. I. Panov","doi":"10.1134/S1064562425700632","DOIUrl":"10.1134/S1064562425700632","url":null,"abstract":"Offline reinforcement learning (RL) often deals with suboptimal data when collecting large expert datasets is unavailable or impractical. This limitation makes it difficult for agents to generalize and achieve high performance, as they must learn primarily from imperfect or inconsistent trajectories. A central challenge is therefore how to best leverage scarce expert demonstrations alongside abundant but lower-quality data. We demonstrate that incorporating even a tiny amount of expert experience can substantially improve RL agent performance. We introduce Re:Frame (Retrieving Experience From Associative Memory), a plug-in module that augments a standard offline RL policy (e.g., Decision Transformer) with a small external Associative Memory Buffer (AMB) populated by expert trajectories drawn from a separate dataset. During training on low-quality data, the policy learns to retrieve expert data from the Associative Memory Buffer (AMB) via content-based associations and integrate them into decision-making; the same AMB is queried at evaluation. This requires no environment interaction and no modifications to the backbone architecture. On D4RL MuJoCo tasks, using as few as 60 expert trajectories (0.1% of a 6000-trajectory dataset), Re:Frame consistently improves over a strong Decision Transformer baseline in three of four settings, with gains up to +10.7 normalized points. These results show that Re:Frame offers a simple and data-efficient way to inject scarce expert knowledge and substantially improve offline RL from low-quality datasets.","PeriodicalId":531,"journal":{"name":"Doklady Mathematics","volume":"112 3","pages":"499 - 505"},"PeriodicalIF":0.6,"publicationDate":"2026-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1134/S1064562425700632.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147560385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Time-Series Modeling with Stochastic Differential Equation Discovery: An Evolutionary Approach 用随机微分方程发现增强时间序列建模：一种进化方法

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425700656

X. Bashkova, A. A. Hvatov

引用次数: 0

Erratum to: Multi-Class Surface Generation of Complex Anatomical Structures Using Neural Networks 使用神经网络的复杂解剖结构的多类表面生成勘误

IF 0.6 4区数学

Doklady Mathematics Pub Date : 2026-03-22 DOI: 10.1134/S1064562425330026

R. UI. Epifanov, Ya. V. Fedotova, D. R. Popov, R. I. Mulliyazhanov

引用次数: 0