Distributed Sensor Networks and Detection Algorithms

Últimos artículos

• An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting

  Jalaj Upadhyay · 25 de septiembre de 2026

  The goal of this note is to give a detailed proof, to the best of our understanding, of the recent presentation by Harrison and Leeman (arXiv:2609.17650v01 and arXiv:2609.17650v02) of the proof by Astra on the lower bound for differentially private continual counting. We believe a more natural and e…

• Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport

  Kim Jakwang, Kwon Dohyun · 22 de septiembre de 2026

  The purpose of this paper is to rigorously quantify the statistical and learning-theoretic properties of adversarial training models for classification. Equivalently, we establish the statistical properties of empirical optimal partial transport. Precisely, first we provide two types of central limi…

• Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent

  Jamie Haddock, Anna Ma, Elizaveta Rebrova · 14 de septiembre de 2026

  We study loss-based filtering for finite-sum optimization with a subset of corrupted component functions whose gradients may be highly unreliable. Motivated by minimum-loss-based SGD (min-$k$-loss) and quantile-based methods for corrupted linear systems, we propose and analyze a general loss-filteri…

• The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures

  Ben Adcock, Michael Griebel, Gregor Maier · 7 de septiembre de 2026

  Operator learning, the approximation of mappings between infinite-dimensional function spaces using machine learning, has gained increasing research attention in recent years. Operator approximations can serve as efficient surrogate models for problems in computational science and engineering, compl…

• Optimal Rates for Agentic Networked Information Aggregation

  MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi, Mahdi JafariRaviz, Shayan Taherijam · 7 de septiembre de 2026

  Building on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures a central pattern in agentic AI: each agent sees only part of the data and passes on only its own conclusion. Their model considers a linear regress…

• ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection

  Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak · 7 de agosto de 2026

  Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment---posing serious risks in safety-critical domains. Recent works have focused on designing scoring functions to quantify OOD uncertainty, with score thresholds …

• An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion

  Jan Nausner, Michael Hubner · 4 de agosto de 2026

  Heterogeneous sensor fusion is vital for detecting, localizing, and classifying CBRNE threats. However, individual sensors are often only capable of detecting a subset of relevant threats with varying reliability or can even provide only indirect threat indications, making threat classification chal…

• Interaction Is Not Necessary for Order-Optimal 1-Bit Mean Estimation

  Jiachen Hu, Han Zhong · 4 de agosto de 2026

  This paper is concerned with one-bit mean estimation, where each independent sample is represented by a single binary message. We consider distributions on $\mathbb{R}$ with mean in $[-\lambda,\lambda]$ and absolute $k$-th central moment at most $\sigma^k$, where $k>1$ is fixed. For this class, prev…

• Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

  Vishnu Bindu Balachandran · 27 de julio de 2026

  Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized P\'olya urn, we prove almost-sure convergence to a mean-field equilibrium whose slope acts as a rep…

• Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning

  Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aur\'elien Bellet · 7 de julio de 2026

  Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as \textit{Byzantine failures}, allowing arbitrarily corrupted communication, or as \textit{data poisoning}, a weaker form of corruption res…

• Efficient learning of bosonic Gaussian unitaries

  Marco Fanizza, Vishnu Iyer, Junseo Lee, Antonio A. Mele, Francesco A. Mele · 26 de junio de 2026

  Bosonic Gaussian unitaries are fundamental building blocks of central continuous-variable quantum technologies such as quantum-optic interferometry and bosonic error-correction schemes. In this work, we present the first time-efficient algorithm for learning bosonic Gaussian unitaries with a rigorou…

• Recovery thresholds for hidden weighted sparse graphs

  Zhe Hou, Jingcheng Liu · 15 de junio de 2026

  Recovering structural information from noisy high-dimensional data is a fundamental task in statistical inference. We investigate the recovery thresholds for a graph hidden in a randomly weighted complete graph. Specifically, an unknown graph $H^* \in H_n$ is chosen uniformly at random, and hidden i…

• Statistical Analysis of using the Shapley Value for Sensor Anomaly Localization with Accurate Classifiers

  Xubin Fang, Rick S. Blum · 2 de junio de 2026

  Recent publications have suggested using the Shap- ley value for sensor anomaly/attack localization. We study the performance of such an approach by using mathematically de- fined optimum binary classifiers in the Shapley value calculation. To judge localization performance, we study the ability of …

• On the Sample Complexity of Robust Binary Hypothesis Testing

  Shankar Vallinayagam, Ankit Pensia, Varun Jog · 26 de mayo de 2026

  We study the sample complexity of robust binary hypothesis testing under three standard contamination models: $\varepsilon$-additive (Huber), $\varepsilon$-subtractive, and $\varepsilon$-total variation (TV), denoted by $n^*_{\mathrm{Hub}}(\varepsilon)$, $n^*_{\mathrm{Sub}}(\varepsilon)$, and $n^*_{…

• FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

  Sanggeon Yun, Ryozo Masukawa, Minhyoung Na, Hyunwoo Oh, Yoshiki Yamaguchi, Wenjun Huang, SungHeon Jeong, Mohsen Imani · 25 de mayo de 2026

  Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to compute and transmit at each point is pivotal; yet as multimo…

• Non-Stationary Online Structured Prediction with Surrogate Losses

  Shinsaku Sakaue, Han Bao, Yuzhou Cao · 15 de mayo de 2026

  Online structured prediction, including online classification as a special case, is the task of sequentially predicting labels from input features. In this setting, the surrogate regret -- the cumulative excess of the actual target loss (e.g., the 0-1 loss) over the surrogate loss (e.g., the logisti…

• Byzantine-Robust Distributed Sparse Learning Revisited

  Yuxuan Wang, Lixin Zhang, Kangqiang Li · 14 de mayo de 2026

  We revisit Byzantine robust distributed estimation for high-dimensional sparse linear models. By combining local $\ell_1$-regularized robust estimation with robust aggregation at the server, the framework applies to pseudo-Huber regression, quantile regression, and sparse SVM. We show that the resul…

• Mean Testing under Truncation beyond Gaussian

  Yuhao Wang, Roberto Imbuzeiro Oliveira, Themis Gouleakis · 5 de mayo de 2026

  We characterize the fundamental limits of high-dimensional mean testing under arbitrary truncation, where samples are drawn from the conditional distribution $P(\cdot \mid S)$ for an unknown truncation set $S$ that may hide up to an $\varepsilon$-fraction of the probability mass. For distributions w…

• Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertainty

  Masoud Ataei, Mohammad Javad Khojasteh, Vikas Dhiman · 4 de mayo de 2026

  We develop a new class of distance-aware error bounds that tightly characterize the approximation error of spline neural networks. Our bottom-up approach analyzes the error bound of each neuron (a spline) and then extends it to the full network. We begin with error bounds for Newton's polynomial, ge…

• Byzantine-tolerant distributed learning of finite mixture models

  Qiong Zhang, Yan Shuo Tan, Jiahua Chen · 22 de abril de 2026

  Traditional statistical methods need to be updated to work with modern distributed data storage paradigms. A common approach is the split-and-conquer framework, which involves learning models on local machines and averaging their parameter estimates. However, this does not work for the important pro…

• Central Limit Theorems for Asynchronous Averaged Q-Learning

  Xingtu Liu · 21 de abril de 2026

  This paper establishes central limit theorems for Polyak-Ruppert averaged Q-learning under asynchronous updates. We prove a non-asymptotic central limit theorem, where the convergence rate in Wasserstein distance explicitly reflects the dependence on the number of iterations, state-action space size…

• Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity

  Ivan Lau, Jonathan Scarlett · 7 de abril de 2026

  In this paper, we study the problem of distributed mean estimation with 1-bit communication constraints. We propose a mean estimator that is based on (randomized and sequentially-chosen) interval queries, whose 1-bit outcome indicates whether the given sample lies in the specified interval. Our esti…

• Central Limit Theorems for Stochastic Gradient Descent Quantile Estimators

  Ziyang Wei, Jiaqi Li, Likai Chen, Wei Biao Wu · 6 de abril de 2026

  This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and techniques, we view quantile SGD iteration as an irreducible, peri…

• State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference

  Peng Sun, Ruoyu Wang, Xue Luo · 6 de abril de 2026

  This paper focuses on the state estimation problem in distributed sensor networks, where intermittent packet dropouts, corrupted observations, and unknown noise covariances coexist. To tackle this challenge, we formulate the joint estimation of system states, noise parameters, and network reliabilit…

• Coded Robust Aggregation for Distributed Learning under Byzantine Attacks

  Chengxi Li, Ming Xiao, Mikael Skoglund · 18 de marzo de 2026

  In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of Byzantine attacks. However, current DL methods apply RBA ru…