检索结果-内蒙古大学图书馆

37th Annual Conference on Learning Theory, COLT 2024

作者： Duchi, John Haque, Saminul Departments of Statistics and Electrical Engineering Stanford University United States Department of Computer Science Stanford University United States

We present an information-theoretic lower bound for the problem of parameter estimation with time-uniform coverage guarantees. Via a new a reduction to sequential testing, we obtain stronger lower bounds that capture the hardness of the time-uniform setting. In the case of location model estimation, logistic regression, and exponential family models, our Ω(√n-1 log log n) lower bound is sharp to within constant factors in typical settings. © 2024 J. Duchi & S. Haque.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Robust Conformal Prediction Using Privileged Information 38

Robust Conformal Prediction Using Privileged Information

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Feldman, Shai Romano, Yaniv Department of Computer Science Technion Israel Departments of Electrical and Computer Engineering and of Computer Science Technion Israel

We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data, such as missing or noisy variables. Our approach builds on conformal prediction, a powerful framework to construct prediction sets that are valid under the i.i.d assumption. Importantly, naively applying conformal prediction does not provide reliable predictions in this setting, due to the distribution shift induced by the corruptions. To account for the distribution shift, we assume access to privileged information (PI). The PI is formulated as additional features that explain the distribution shift, however, they are only available during training and absent at test time. We approach this problem by introducing a novel generalization of weighted conformal prediction and support our method with theoretical coverage guarantees. Empirical experiments on both real and synthetic datasets indicate that our approach achieves a valid coverage rate and constructs more informative predictions compared to existing methods, which are not supported by theoretical guarantees. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Universally Instance-Optimal Mechanisms for Private Statistical Estimation 37

Universally Instance-Optimal Mechanisms for Private Statisti...

引用

37th Annual Conference on Learning Theory, COLT 2024

作者： Asi, Hilal Duchi, John C. Haque, Saminul Li, Zewei Ruan, Feng Apple United States Departments of Statistics and Electrical Engineering Stanford University United States Department of Computer Science Stanford University United States Department of Statistics and Data Science Northwestern University United States

We consider the problem of instance-optimal statistical estimation under the constraint of differential privacy where mechanisms must adapt to the difficulty of the input dataset. We prove a new instance specific lower bound using a new divergence and show it characterizes the local minimax optimal rates for private statistical estimation. We propose two new mechanisms that are universally instance-optimal for general estimation problems up to logarithmic factors. Our first mechanism, the total variation mechanism, builds on the exponential mechanism with stable approximations of the total variation distance, and is universally instance-optimal in the high privacy regime Ε ≤ 1/√n. Our second mechanism, the T-mechanism, is based on the T-estimator framework (Birgé, 2006) using the clipped log likelihood ratio as a stable test: it attains instance-optimal rates for any Ε ≤ 1 up to logarithmic factors. Finally, we study the implications of our results to robust statistical estimation, and show that our algorithms are universally optimal for this problem, characterizing the optimal minimax rates for robust statistical estimation. © 2024 H. Asi, J.C. Duchi, S. Haque, Z. Li & F. Ruan.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Trade-Offs Between Amortization and Download Bandwidth for Linear HSS 5

Improved Trade-Offs Between Amortization and Download Bandwi...

引用

5th Conference on Information-Theoretic Cryptography, ITC 2024

作者： Blackwell, Keller Wootters, Mary Department of Computer Science Stanford University CA United States Departments of Computer Science and Electrical Engineering Stanford University CA United States

ISBN: (纸本)9783959773331

A Homomorphic Secret Sharing (HSS) scheme is a secret-sharing scheme that shares a secret x among s servers, and additionally allows an output client to reconstruct some function f(x) using information that can be locally computed by each server. A key parameter in HSS schemes is download rate, which quantifies how much information the output client needs to download from the servers. Often, download rate is improved by amortizing over instances of the problem, making also a key parameter of interest. Recent work [23] established a limit on the download rate of linear HSS schemes for computing low-degree polynomials and constructed schemes that achieve this optimal download rate;their schemes required amortization over = Ω(s log(s)) instances of the problem. Subsequent work [6] completely characterized linear HSS schemes that achieve optimal download rate in terms of a coding-theoretic notion termed optimal labelweight codes. A consequence of this characterization was that = Ω(s log(s)) is in fact necessary to achieve optimal download rate. In this paper, we characterize all linear HSS schemes, showing that schemes of any download rate are equivalent to a generalization of optimal labelweight codes. This equivalence is constructive and provides a way to obtain an explicit linear HSS scheme from any linear code. Using this characterization, we present explicit linear HSS schemes with slightly sub-optimal rate but with much improved amortization = O(s). Our constructions are based on algebraic geometry codes (specifically Hermitian codes and Goppa codes). © Keller Blackwell and Mary Wootters.

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Resampling methods for private statistical inference

arXiv

引用

arXiv 2024年

作者： Chadha, Karan Duchi, John C. Kuditipudi, Rohith Departments of Electrical Engineering Departments of Statistics Departments of Computer Science Stanford University United States

We propose two private variants of the non-parametric bootstrap for privately computing confidence sets. Each privately computes the median of results of multiple "little" bootstraps, yielding asymptotic bounds on the coverage error of the resulting confidence sets. For a fixed differential privacy parameter Ε, our methods enjoy the same error rates as the non-private bootstrap to within logarithmic factors in the sample size n. We empirically validate the performance of our methods for mean estimation, median estimation, and logistic regression, and our methods achieve similar coverage accuracy to existing methods (and non-private baselines) while providing notably shorter (about 10×) confidence intervals than previous approaches. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Convolutional neural network-based image watermarking using discrete wavelet transform

引用

International Journal of Information Technology (Singapore) 2023年第4期15卷 2021-2029页

作者： Tavakoli, Alireza Honjani, Zahra Sajedi, Hedieh Department of Computer Engineering School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Computer Science School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran

With the growing popularity of the Internet, digital images are used and transferred more frequently. Although this phenomenon facilitates easy access to information, it also creates security concerns and violates intellectual property rights by allowing illegal use, copying, and digital content theft. Using watermarks in digital images is one of the most common ways to maintain security. Watermarking is proving and declaring ownership of an image by adding a digital watermark to the original image. Watermarks can be either text or an image placed overtly or covertly in an image and are expected to be challenging to remove. This paper proposes a combination of convolutional neural networks (CNNs) and wavelet transforms to obtain a watermarking network for embedding and extracting watermarks. The network is independent of the host image resolution, can accept all kinds of watermarks, and has only 11 layers while keeping performance. Performance is measured by two terms;the similarity between the extracted watermark and the original one and the similarity between the host image and the watermarked one. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Convolutional neural networks Neural networks Watermarking Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Performance-Guaranteed Finite-Time Tracking of Strict-Feedback Systems with Unknown Control Directions: A Novel Switching Mechanism

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4061-4068页

作者： Mao, Bing Wu, Xiaoqun Fan, Ziye Lu, Jinhu Chen, Guanrong Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Wuhan University School of Mathematics and Statistics Hubei430072 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Electrical Engineering Hong Kong Hong Kong

The problem of achieving performance-guaranteed finite-time exact tracking for uncertain strict-feedback nonlinear systems with unknown control directions is addressed. A novel logic switching mechanism with monitoring functions is designed to deal with unknown control directions. This approach is different from existing methods like the Nussbaum gain technique and smooth orientation functions, which are inapplicable to finite-time exact tracking. The main challenge lies in designing monitoring functions and determining switching rules, which is well resolved through three steps. Most significantly, in contrast to existing works that solely guarantee bounded tracking or asymptotic exact tracking, the new mechanism incorporates novel integral sliding mode techniques to achieve finite-time exact tracking with guaranteed performance. Finally, simulations are presented with comparison to demonstrate the effectiveness of the proposed methods. © 1963-2012 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Invertibility of Discrete-Time Linear Systems with Sparse Inputs 63

Invertibility of Discrete-Time Linear Systems with Sparse In...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Poe, Kyle Mallada, Enrique Vidal, Rene University of Pennsylvania Applied Mathematics and Computational Science Group PA19104 United States Johns Hopkins University Mallada Is with the Department of Electrical and Computer Engineering MD21218 United States University of Pennsylvania Radiology Computer and Information Science Statistics and Data Science Departments of Electrical and Systems Engineering PA19104 United States

ISBN: (纸本)9798350316339

One of the fundamental problems of interest for discrete-time linear systems is whether its input sequence may be recovered given its output sequence, a.k.a. the left inversion problem. Many conditions on the state space geometry, dynamics, and spectral structure of a system have been used to characterize the well-posedness of this problem, without assumptions on the inputs. However, certain structural assumptions, such as input sparsity, have been shown to translate to practical gains in the performance of inversion algorithms, surpassing classical guarantees. Establishing necessary and sufficient conditions for left invertibility of systems with sparse inputs is therefore a crucial step toward understanding the performance limits of system inversion under structured input assumptions. In this work, we provide the first necessary and sufficient characterizations of left invertibility for linear systems with sparse inputs, echoing classic characterizations for standard linear systems. The key insight in deriving these results is in establishing the existence of two novel geometric invariants unique to the sparseinput setting, the weakly unobservable and strongly reachable subspace arrangements. By means of a concrete example, we demonstrate the utility of these characterizations. We conclude by discussing extensions and applications of this framework to several related problems in sparse control. © 2024 IEEE.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Accelerated gradient methods for nonconvex optimization: Escape trajectories from strict saddle points and convergence to local minima

arXiv

引用

arXiv 2023年

作者： Dixit, Rishabh Gürbüzbalaban, Mert Bajwa, Waheed U. Department of Electrical and Computer Engineering Departments of Electrical & Computer Engineering Management Science and Information Systems and Statistics United States Departments of Electrical & Computer Engineering and Statistics

This paper considers the problem of understanding the behavior of a general class of accelerated gradient methods on smooth nonconvex functions. Motivated by some recent works that have proposed effective algorithms, based on Polyak’s heavy ball method and the Nesterov accelerated gradient method, to achieve convergence to a local minimum of nonconvex functions, this work proposes a broad class of Nesterov-type accelerated methods and puts forth a rigorous study of these methods encompassing the escape from saddle-points and convergence to local minima through a both asymptotic and a nonasymptotic analysis. In the asymptotic regime, this paper answers an open question of whether Nesterov’s accelerated gradient method (NAG) with variable momentum parameter avoids strict saddle points almost surely. This work also develops two metrics of asymptotic rate of convergence and divergence, and evaluates these two metrics for several popular standard accelerated methods such as the NAG, and Nesterov’s accelerated gradient with constant momentum (NCM) near strict saddle points. In the local regime, this work provides an analysis that leads to the "linear" exit time estimates from strict saddle neighborhoods for trajectories of these accelerated methods as well the necessary conditions for the existence of such trajectories. Finally, this work studies a sub-class of accelerated methods that can converge in convex neighborhoods of nonconvex functions with a near optimal rate to a local minima and at the same time this sub-class offers superior saddle-escape behavior compared to that of NAG. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Cyberattack Detection in Blockchain-Based IoT Systems Using AI and Homomorphic Encryption

引用

IEEE Internet of Things Journal 2025年第11期12卷 16478-16492页

作者： Manh, Bui Duc Nguyen, Chi-Hieu Hoang, Dinh Thai Nguyen, Diep N. Zeng, Ming Pham, Quoc-Viet University of Technology Sydney School of Electrical and Data Engineering SydneyNSW2007 Australia Université Laval Department of Electrical Engineering and Computer Engineering QuebecQCG1V 0A6 Canada University of Dublin School of Computer Science and Statistics Trinity College Dublin D02 PN40 Ireland

This work proposes a novel privacy-preserving cyberattack detection framework for blockchain-based Internet-of-Things (IoT) systems. In our approach, artificial intelligence (AI)-driven detection modules are strategically deployed at blockchain nodes to identify real-time attacks, ensuring high accuracy and minimal delay. To achieve this efficiency, the model training is conducted by a cloud service provider (CSP). Accordingly, blockchain nodes send their data to the CSP for training, but to safeguard privacy, the data is encrypted using homomorphic encryption (HE) before transmission. This encryption method allows the CSP to perform computations directly on encrypted data without the need for decryption, preserving data privacy throughout the learning process. To handle the substantial volume of encrypted data, we introduce an innovative packing algorithm in a Single-Instruction-Multiple-Data (SIMD) manner, enabling efficient training on HE-encrypted data. Building on this, we develop a novel deep neural network training algorithm optimized for encrypted data. We further propose a privacy-preserving distributed learning approach based on the FedAvg algorithm, which parallelizes the training across multiple workers, significantly improving computation time. Upon completion, the CSP distributes the trained model to the blockchain nodes, enabling them to perform real-time, privacy-preserved detection. Our simulation results demonstrate that our proposed method can not only mitigate the training time but also achieve detection accuracy that is approximately identical to the approach without encryption, with a gap of around 0.01%. Additionally, our real implementations on various blockchain consensus algorithms and hardware configurations show that our proposed framework can also be effectively adapted to real-world systems. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：