IEEE Transactions on Information Theory最新文献_第7页

Fréchet Regression With Mondrian Forests: Finite-Sample Guarantees and Ensemble Benefits 蒙德里安森林的fracimchet回归：有限样本保证和集合效益

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-07 DOI: 10.1109/TIT.2026.3681693

Rui Qiu;Fang Yao;Zhou Yu

{"title":"Fréchet Regression With Mondrian Forests: Finite-Sample Guarantees and Ensemble Benefits","authors":"Rui Qiu;Fang Yao;Zhou Yu","doi":"10.1109/TIT.2026.3681693","DOIUrl":"https://doi.org/10.1109/TIT.2026.3681693","url":null,"abstract":"Fréchet random forests extend the power of classical random forests to general metric spaces, offering promising advantages over traditional methods, especially in high-dimensional settings. While forests have empirically outperformed individual trees in Fréchet regression, the theoretical basis for this improvement remains largely unexplored. This paper fills this gap by establishing non-asymptotic upper bounds for the prediction risk of Fréchet Mondrian forests, complementing the existing literature that primarily focuses on asymptotic analysis. We demonstrate that, under suitable regularity conditions, Fréchet Mondrian forests attain convergence rates comparable to their Euclidean counterparts. Moreover, under higher-order smoothness assumptions and with a sufficient number of trees, Fréchet forests achieve faster convergence than individual Fréchet trees, thereby providing a rigorous theoretical justification for the benefit of ensembles in non-Euclidean regression problems. The effectiveness of the proposed method is further corroborated through simulation studies across diverse settings, including probability distributions, symmetric positive-definite matrices, and spherical data.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"4221-4245"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simultaneous Inference for Covariance and Precision Matrices of Long-Range Dependent Time Series 长期相关时间序列的协方差和精度矩阵的同时推理

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-20 DOI: 10.1109/TIT.2026.3685246

Percy S. Zhai;Mladen Kolar;Wei Biao Wu

引用次数: 0

Phase Retrieval and Matrix Sensing via Benign and Overparametrized Nonconvex Optimization 基于良性和超参数化非凸优化的相位检索和矩阵感知

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-16 DOI: 10.1109/TIT.2026.3684748

Andrew D. McRae

{"title":"Phase Retrieval and Matrix Sensing via Benign and Overparametrized Nonconvex Optimization","authors":"Andrew D. McRae","doi":"10.1109/TIT.2026.3684748","DOIUrl":"https://doi.org/10.1109/TIT.2026.3684748","url":null,"abstract":"We study a nonconvex optimization algorithmic approach to phase retrieval and the more general problem of semidefinite low-rank matrix sensing. Specifically, we analyze the nonconvex landscape of a quartic Burer-Monteiro factored least-squares optimization problem. We develop a new analysis framework, taking advantage of the semidefinite problem structure, to understand the properties of second-order critical points—specifically, whether they (approximately) recover the ground truth matrix. We show that it can be helpful to (mildly) overparametrize the problem, that is, to optimize over matrices of higher rank than the ground truth. We then apply this framework to several well-studied problem instances: in addition to recovering existing state-of-the-art phase retrieval landscape guarantees (without overparametrization), we show that overparametrizing by a factor at most logarithmic in the dimension allows recovery with optimal statistical sample complexity and error for the problems of: 1) phase retrieval with sub-Gaussian measurements; and 2) more general semidefinite matrix sensing with rank-1 Gaussian measurements. Previously, such statistical results had been shown only for estimators based on semidefinite programming. More generally, our analysis is partially based on the powerful method of convex dual certificates, suggesting that it could be applied to a much wider class of problems.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"4203-4220"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rotation-Symmetric Bent Functions Outside the Completed Maiorana-McFarland Class 已完成的Maiorana-McFarland类之外的旋转对称弯曲函数

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-17 DOI: 10.1109/TIT.2026.3685133

Alexandr Polujan;Sadmir Kudin;Enes Pasalic

{"title":"Rotation-Symmetric Bent Functions Outside the Completed Maiorana-McFarland Class","authors":"Alexandr Polujan;Sadmir Kudin;Enes Pasalic","doi":"10.1109/TIT.2026.3685133","DOIUrl":"https://doi.org/10.1109/TIT.2026.3685133","url":null,"abstract":"Rotation-symmetric (RS) bent functions, which are invariant under the action of the cyclic group, have attracted significant attention over the past three decades due to their importance in cryptographic applications. For the last three decades of research on these objects, most known RS bent functions have been obtained by applying extended-affine equivalence to specific Maiorana-McFarland bent functions, in a way that ensures the resulting function retains invariance under the cyclic group action. Due to the intrinsic difficulty of characterizing RS bent functions that do not belong to the completed Maiorana-McFarland class <inline-formula> <tex-math>$mathcal {M}^{#}$ </tex-math></inline-formula>, there has been no evidence for the existence of such functions until now. In this paper, we provide, for the first time, a solution to this problem. First, we perform a computational classification of RS cubic bent functions in ten variables under extended-affine equivalence and demonstrate that one of the resulting classes is outside the <inline-formula> <tex-math>$mathcal {M}^{#}$ </tex-math></inline-formula> class. Next, we prove that an infinite family of RS bent functions on <inline-formula> <tex-math>$mathbb {F}_{2}^{n}$ </tex-math></inline-formula> of maximum algebraic degree <inline-formula> <tex-math>$n/2$ </tex-math></inline-formula> (Su, Adv. Math. Commun. 13(2): 253–265, 2019) does not belong to <inline-formula> <tex-math>$mathcal {M}^{#}$ </tex-math></inline-formula>, for all <inline-formula> <tex-math>$n ge 8$ </tex-math></inline-formula>. Finally, we show that a family of quartic RS bent functions on <inline-formula> <tex-math>$mathbb {F}_{2}^{n}$ </tex-math></inline-formula> (Carlet, Gao, and Liu, J. Comb. Theory Ser. A 127: 161–175, 2014), does not belong to the <inline-formula> <tex-math>$mathcal {M}^{#}$ </tex-math></inline-formula> class for infinitely many <inline-formula> <tex-math>$n$ </tex-math></inline-formula>.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"4341-4351"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Classical Communication Over Quantum Multiple-Access Channel With Unreliable Entanglement Assistance 不可靠纠缠辅助下量子多址信道的经典通信

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-02 DOI: 10.1109/TIT.2026.3680133

Xiaomin Liu;Zhengjun Xi

引用次数: 0

Error Exponents of Quantum State Discrimination With Composite Correlated Hypotheses 基于复合相关假设的量子态判别误差指数

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-16 DOI: 10.1109/TIT.2026.3684314

Kun Fang;Masahito Hayashi

{"title":"Error Exponents of Quantum State Discrimination With Composite Correlated Hypotheses","authors":"Kun Fang;Masahito Hayashi","doi":"10.1109/TIT.2026.3684314","DOIUrl":"https://doi.org/10.1109/TIT.2026.3684314","url":null,"abstract":"We study the error exponents in quantum hypothesis testing between two sets of quantum states, extending the analysis beyond the independent and identically distributed case to encompass composite correlated hypotheses. In particular, we introduce and compare two natural extensions of the quantum Hoeffding divergence and anti-divergence to sets of quantum states, establishing their equivalence or quantitative relations. In the error exponent regime, we generalize the quantum Hoeffding bound to stable sequences of convex, compact sets of quantum states, demonstrating that the optimal Type-I error exponent, under an exponential constraint on the Type-II error, is precisely characterized by the regularized quantum Hoeffding divergence between the sets. In the strong converse exponent regime, we establish a general lower bound on the exponent in terms of the regularized quantum Hoeffding anti-divergence, and we prove a matching upper bound when the null hypothesis is a singleton, under additional assumptions. The generality of these results enables applications in various contexts, including (i) refining the generalized quantum Stein’s lemma by Fang et al. (2024); (ii) exhibiting counterexamples to the continuity of the regularized Petz Rényi divergence and Hoeffding divergence; (iii) obtaining error exponents for adversarial channel discrimination and resource detection problems.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"4140-4165"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Asymptotic Analysis of Max–Min SINR in Downlink MISO System With Multi-Weighted Power Constraints 多加权功率约束下MISO系统最大-最小信噪比的渐近分析

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-06 DOI: 10.1109/TIT.2026.3680284

Shasha Liu;Abla Kammoun;Hayssam Dahrouj;Mohamed-Slim Alouini

{"title":"Asymptotic Analysis of Max–Min SINR in Downlink MISO System With Multi-Weighted Power Constraints","authors":"Shasha Liu;Abla Kammoun;Hayssam Dahrouj;Mohamed-Slim Alouini","doi":"10.1109/TIT.2026.3680284","DOIUrl":"https://doi.org/10.1109/TIT.2026.3680284","url":null,"abstract":"This work addresses the fundamental problem related to the characterization of the parameters of optimal precoders at the asymptotic regime, a topic of increasing interest given the upsurge in massively connected networks and their emerging applications. The paper, particularly, focuses on the downlink of a single-cell multi-user system, where a base station (BS) equipped with <inline-formula> <tex-math>$M$ </tex-math></inline-formula> antennas communicates with <inline-formula> <tex-math>$K$ </tex-math></inline-formula> single-antenna users. We then propose a low-complexity design for the optimal linear precoder (OLP) that maximizes the minimum signal-to-interference-plus-noise ratio (SINR) while ensuring multi-weighted power constraints. To achieve this, we consider the asymptotic regime where <inline-formula> <tex-math>$M$ </tex-math></inline-formula> and <inline-formula> <tex-math>$K$ </tex-math></inline-formula> grow large while maintaining a fixed ratio. Utilizing tools from random matrix theory (RMT), we derive explicit deterministic approximations for the parameters of the OLP and the allocated powers for users. One of the paper highlights is that the approximations provide deeper insight into the structure of the optimal precoders, predict the active weighted power constraints, and significantly reduce the implementation complexity in large-scale networks. Another paper highlight is how to analyze best scenarios where the power weights for some users are exactly zero, a case not addressed. We revisit the original OLP, presenting an implementation that accommodates zero-power weights and propose its equivalent low-complexity asymptotic design. Numerical results are used to validate the asymptotic analysis is accurate in the finite system regime and investigate the impact of weighted power constraints on the system energy efficiency (EE).","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"4365-4398"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Poisson Hail on a Wireless Ground 无线地面上的泊松冰雹

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-27 DOI: 10.1109/TIT.2026.3687309

François Baccelli;Ke Feng;Sergey Foss

{"title":"Poisson Hail on a Wireless Ground","authors":"François Baccelli;Ke Feng;Sergey Foss","doi":"10.1109/TIT.2026.3687309","DOIUrl":"https://doi.org/10.1109/TIT.2026.3687309","url":null,"abstract":"This paper defines a new model which incorporates three key ingredients of a large class of wireless communication systems: 1) spatial interactions through interference, (1) dynamics of the queueing type, with users joining and leaving, and 2) carrier sensing and collision avoidance as used in, e.g., WiFi. In systems using (2), rather than directly accessing the shared resources upon arrival, a customer is considerate and waits to access them until nearby users in service have left. This new model can be seen as a missing piece of a larger puzzle that contains such dynamics as spatial birth-and-death processes, the Poisson-Hail model, and wireless dynamics as key other pieces. It is shown that, under natural assumptions, this model can be represented as a Markov process on the space of counting measures. The main results are then two-fold. The first result is on the shape of the stability region and, more precisely, on the characterization of the critical value of the arrival rate that separates stability from instability. The second result is of a more qualitative or perhaps even ethical nature. There is evidence that for natural values of the system parameters, the implementation of sensing and the delayed access for collision avoidance can stabilize a system that would be unstable if immediate access to the shared resources would be granted. In other words, for these parameters, renouncing greedy access makes sharing sustainable, whereas indulging in greedy access kills the system.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"3651-3664"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Binary Reconstruction Codes for Correcting One Deletion and One Substitution 修正一次删除和一次替换的二进制重构码

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-28 DOI: 10.1109/TIT.2026.3688516

Yuling Li;Yubo Sun;Gennian Ge

{"title":"Binary Reconstruction Codes for Correcting One Deletion and One Substitution","authors":"Yuling Li;Yubo Sun;Gennian Ge","doi":"10.1109/TIT.2026.3688516","DOIUrl":"https://doi.org/10.1109/TIT.2026.3688516","url":null,"abstract":"In this paper, we investigate binary reconstruction codes capable of correcting one deletion and one substitution. We define the <italic>single-deletion single-substitution ball</i> function <inline-formula> <tex-math>$ mathcal {B} $ </tex-math></inline-formula> as a mapping from a sequence to the set of sequences that can be derived from it by performing one deletion and one substitution. A binary <inline-formula> <tex-math>$(n,N;mathcal {B})$ </tex-math></inline-formula><italic>-reconstruction code</i> is defined as a collection of binary sequences of length <inline-formula> <tex-math>$ n $ </tex-math></inline-formula> such that the intersection size between the single-deletion single-substitution balls of any two distinct codewords is strictly less than <inline-formula> <tex-math>$ N $ </tex-math></inline-formula>. This property ensures that each codeword can be uniquely reconstructed from <inline-formula> <tex-math>$ N $ </tex-math></inline-formula> distinct elements in its single-deletion single-substitution ball. Our main contribution is to demonstrate that when <inline-formula> <tex-math>$ N $ </tex-math></inline-formula> is set to <inline-formula> <tex-math>$ 4n - 8 $ </tex-math></inline-formula>, <inline-formula> <tex-math>$ 3n - 4 $ </tex-math></inline-formula>, <inline-formula> <tex-math>$ 2n + 9 $ </tex-math></inline-formula>, <inline-formula> <tex-math>$ n+21 $ </tex-math></inline-formula>, 31, and 7, the redundancy of binary <inline-formula> <tex-math>$(n,N;mathcal {B})$ </tex-math></inline-formula>-reconstruction codes can be 0, 1, 2, <inline-formula> <tex-math>$ log log n + 3 $ </tex-math></inline-formula>, <inline-formula> <tex-math>$ log n + 1 $ </tex-math></inline-formula>, and <inline-formula> <tex-math>$ 3log n + 4 $ </tex-math></inline-formula>, respectively, where the logarithm is on base two.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"3733-3752"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

On the Strong Converse Exponent and Error Exponent of the Classical Soft Covering 经典软覆盖的强逆指数和误差指数

IF 2.6 3区计算机科学

IEEE Transactions on Information Theory Pub Date : 2026-06-01 Epub Date: 2026-04-01 DOI: 10.1109/TIT.2026.3680014

Xingyi He;S. Sandeep Pradhan;Andreas Winter

{"title":"On the Strong Converse Exponent and Error Exponent of the Classical Soft Covering","authors":"Xingyi He;S. Sandeep Pradhan;Andreas Winter","doi":"10.1109/TIT.2026.3680014","DOIUrl":"https://doi.org/10.1109/TIT.2026.3680014","url":null,"abstract":"This paper establishes the exact strong converse exponent of the soft covering problem in the classical setting. This exponent characterizes the slowest achievable convergence speed of the total variation to one when a code of rate below mutual information is applied to a discrete memoryless channel for synthesizing a product output distribution. The proposed exponent is expressed through a new two-parameter information quantity, differing from the more commonly studied Rényi divergence or Rényi mutual information. In addition, we demonstrate the non-tightness of random coding for rates both below and above mutual information. Discussions on the latter start with noiseless channels, where we develop a deterministic code construction that outperforms random codes in error exponents. We further observe that the conventional formulation, which assumes a uniform distribution over messages, inherently introduces a discrepancy in error exponents depending on whether the components of the target distribution are rational or irrational numbers. To eliminate this discrepancy, we propose a new formulation in which messages are allowed to be distributed non-uniformly, and the rate is given by the logarithm of the smallest nonzero message probability (corresponding to Rényi entropy <inline-formula> <tex-math>$H_{-infty }$ </tex-math></inline-formula> of order <inline-formula> <tex-math>$-infty $ </tex-math></inline-formula>). The exact error exponent is characterized in this formulation for noiseless channels. Furthermore, for noisy channels, we provide a high-rate improvement in achievability and derive a converse bound on the error exponent.","PeriodicalId":13494,"journal":{"name":"IEEE Transactions on Information Theory","volume":"72 6","pages":"3621-3650"},"PeriodicalIF":2.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0