检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

262 篇 期刊文献
169 篇 会议
3 册 图书
2 篇 学位论文
2 篇 资讯

馆藏范围

438 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

348 篇 工学
- 266 篇 计算机科学与技术...
- 102 篇 电气工程
- 81 篇 控制科学与工程
- 32 篇 信息与通信工程
- 31 篇 软件工程
- 3 篇 机械工程
- 3 篇 仪器科学与技术
- 3 篇 电子科学与技术（可...
- 1 篇 测绘科学与技术
- 1 篇 石油与天然气工程
- 1 篇 农业工程
- 1 篇 生物医学工程（可授...
- 1 篇 生物工程
136 篇 理学
- 109 篇 数学
- 21 篇 统计学（可授理学、...
- 15 篇 物理学
- 10 篇 系统科学
- 9 篇 生物学
- 2 篇 化学
24 篇 管理学
- 22 篇 管理科学与工程(可...
- 1 篇 工商管理
- 1 篇 图书情报与档案管...
6 篇 经济学
- 4 篇 理论经济学
- 3 篇 应用经济学
5 篇 医学
- 5 篇 基础医学(可授医学...
- 4 篇 临床医学
- 1 篇 特种医学
- 1 篇 医学技术（可授医学...
2 篇 文学
- 2 篇 新闻传播学
2 篇 农学
- 1 篇 作物学

主题

438 篇 sample complexit...
40 篇 pac learning
26 篇 reinforcement le...
21 篇 statistical lear...
20 篇 machine learning
19 篇 active learning
16 篇 complexity theor...
15 篇 algorithms
12 篇 compressed sensi...
12 篇 learning
10 篇 lower bound
10 篇 online learning
9 篇 selective sampli...
9 篇 generalization
9 篇 dictionary learn...
8 篇 deep learning
8 篇 learning theory
8 篇 stochastic optim...
7 篇 sequential desig...
7 篇 matrices

机构

6 篇 google
5 篇 mpi for intellig...
4 篇 carnegie mellon ...
4 篇 georgia inst tec...
4 篇 toyota technol i...
4 篇 mit cambridge ma...
4 篇 carnegie mellon ...
4 篇 univ hong kong p...
4 篇 natl univ singap...
4 篇 georgia inst tec...
3 篇 columbia univers...
3 篇 princeton univ d...
3 篇 technion israel ...
3 篇 tata inst fundam...
3 篇 microsoft res re...
3 篇 univ illinois co...
3 篇 univ florida dep...
3 篇 uc berkeley
3 篇 hebrew univ jeru...
3 篇 harvard univ cam...

作者

12 篇 hanneke steve
7 篇 huang zhiyi
6 篇 bernhard schölko...
6 篇 kevin murphy
6 篇 balcan maria-flo...
5 篇 mansour yishay
5 篇 long pm
5 篇 sivan sabato
5 篇 steve hanneke
5 篇 oymak samet
5 篇 zhivotovskiy nik...
4 篇 roughgarden tim
4 篇 roch sebastien
4 篇 sabato sivan
4 篇 gribonval remi
4 篇 mohammadi hesame...
4 篇 shamir ohad
4 篇 srebro nathan
4 篇 shai shalev-shwa...
4 篇 jovanovic mihail...

语言

428 篇 英文
10 篇 其他

检索条件"主题词=Sample complexity"

共 438 条记录，以下是81-90 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Near-optimal sample complexity bounds for circulant binary embedding

Near-optimal sample complexity bounds for circulant binary e...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Samet Oymak Christos Thrampoulidis Babak Hassibi Google Inc. United States of America California Institute of Technology United States of America

ISBN: (纸本)9781509041183

Binary embedding is the problem of mapping points from a high-dimensional space to a Hamming cube in lower dimension while preserving pairwise distances. An efficient way to accomplish this is to make use of fast embedding techniques involving Fourier transform e.g. circulant matrices. While binary embedding has been studied extensively, theoretical results on fast binary embedding are rather limited. In this work, we build upon the recent literature to obtain significantly better dependencies on the problem parameters. A set of N points in R~n can be properly embedded into the Hamming cube {±1}~k with δ distortion, by using k ～ δ~(-3) log N samples which is optimal in the number of points N and compares well with the optimal distortion dependency δ~(-2). Our optimal embedding result applies in the regime log N ≤ n~(1/3). Furthermore, if the looser condition log N ≤ √n holds, we show that all but an arbitrarily small fraction of the points can be optimally embedded. We believe the proposed techniques can be useful to obtain improved guarantees for other nonlinear embedding problems.

关键词： embedding sample complexity circulation Binary radon nitrogen Optimal

来源：评论

学校读者我要写书评

暂无评论

On the sample complexity of Robust PCA 12

On the Sample Complexity of Robust PCA

引用

Annual Conference on Neural Information Processing Systems

作者： Matthew Coudron Gilad Lennan Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA 02139 School of Mathematics University of Minnesota Minneapolis MN 55455

ISBN: (纸本)9781627480031

We estimate the rate of convergence and sample complexity of a recent robust estimator for a generalized version of the inverse covariance matrix. This estimator is used in a convex algorithm for robust subspace recovery (i.e., robust PCA). Our model assumes a sub-Gaussian underlying distribution and an i.i.d. sample from it. Our main result shows with high probability that the norm of the difference between the generalized inverse covariance of the underlying distribution and its estimator from an i.i.d. sample of size N is of order O(N~(-0.5+ε)) for arbitrarily small ε > 0 (affecting the probabilistic estimate); this rate of convergence is close to the one of direct covariance estimation, i.e., O(N~(0.5)). Our precise probabilistic estimate implies for some natural settings that the sample complexity of the generalized inverse covariance estimation when using the Frobenius norm is O(D~(2+δ)) for arbitrarily small S > 0 (whereas the sample complexity of direct covariance estimation with Frobenius norm is O(D2)). These results provide similar rates of convergence and sample complexity for the corresponding robust subspace recovery algorithm. To the best of our knowledge, this is the only work analyzing the sample complexity of any robust PCA algorithm.

关键词： sample complexity Euclidean matrix norm Converge Covariance principal components analysis Passive Cutaneous Anaphylaxis Probability Generalized inverse

来源：评论

学校读者我要写书评

暂无评论

Analysing the sample complexity of Opponent Shaping 24

Analysing the Sample Complexity of Opponent Shaping

引用

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems

作者： Kitty Fung Qizhen Zhang Chris Lu Jia Wan Timon Willi Jakob Foerster University of Oxford Oxford United Kingdom Massachusetts Institute of Technology Massachutsetts MA USA

ISBN: (纸本)9798400704864

Learning in general-sum games often yields collectively sub-optimal results. Addressing this, opponent shaping (OS) methods actively guide the learning processes of other agents, empirically leading to improved individual and group performances. Early OS methods use higher-order derivatives to shape the learning of co-players, making them unsuitable to shape multiple learning steps. Follow-up work Model-free Opponent Shaping (M-FOS) addresses the short-comings of earlier OS methods by reframing the OS problem into a meta-game. In contrast to early OS methods, there is little theoretical understanding of the M-FOS framework. Providing theoretical guarantees for M-FOS is hard because A) there is little literature on theoretical sample complexity bounds for meta-reinforcement learning; B) M-FOS operates in continuous state and action spaces hence theoretical analysis is challenging. In this work, we present R-FOS, a tabular version of M-FOS that is more suitable for theoretical analysis. R-FOS discretises the continuous meta-game MDP into a tabular MDP. Within this discretised MDP, we adapt the Rmax algorithm, most prominently used to derive PAC-bounds for MDPs, as the meta-learner in the R-FOS algorithm. We derive a sample complexity bound that is exponential in the cardinality of the inner state and action space and the number of agents. Our bound guarantees that, with high probability, the optimal policy learned by an R-FOS agent can get close to the optimal policy, apart from a constant factor. Finally, we investigate how R-FOS's sample complexity scales in the size of state-action space. Our theoretical results on scaling are supported empirically in the Matching Pennies environment.

关键词： meta reinforcement learning multi-agent opponent shaping reinforcement learning sample complexity

来源：评论

学校读者我要写书评

暂无评论

Consistent Online Gaussian Process Regression Without the sample complexity Bottleneck

Consistent Online Gaussian Process Regression Without the Sa...

引用

American Control Conference

作者： Alec Koppel Computational and Information Sciences Directorate U.S. Army Research Laboratory Adelphi MD 20783 USA

ISBN: (纸本)9781538679012;9781538679265

Gaussian process regression provides a framework for nonlinear nonparametric Bayesian inference applicable across machine learning, robotics, chemical engineering, and other settings. Unfortunately, the computational burden of the posterior mean and covariance scales cubically with the training sample size. Even worse, in the online setting where samples perpetually arrive, this complexity approaches infinity. Thus, popular perception is that Gaussian processes cannot be used with streaming data, and that approximations are required. Motivated by this necessity, we develop the first compression sub-routine for online Gaussian processes that preserves their convergence to the population posterior, i.e., asymptotic posterior consistency, while ameliorating their intractable complexity growth with the sample size. We do so by after each sequential Bayesian update, fixing an error neighborhood with respect to the Hellinger metric centered at the current empirical probability measure, and greedily tossing out past kernel dictionary elements until we hit the boundary of this neighborhood. We call the resulting method Parsimonious Online Gaussian Processes (POG). When we set the error radius, or compression budget, go to null with the sample size, then exact asymptotic consistency is preserved (Theorem li) at the cost of unbounded memory in the limit. On the other hand, for constant compression budget, POG converges to a neighborhood of the population posterior distribution (Theorem 1ii) but with finite memory that is at-worst determined by the metric entropy of the feature space (Theorem 2). Experiments on benchmark data demonstrates that POG exhibits favorable performance in practice.

关键词： Gaussian processes sample Size sample complexity Bayesian inference Theorem Gauss

来源：评论

学校读者我要写书评

暂无评论

The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and sample complexity 21

The Price of Incentivizing Exploration: A Characterization v...

引用

Proceedings of the 22nd ACM Conference on Economics and Computation

作者： Mark Sellke Aleksandrs Slivkins Stanford University Stanford IN USA Microsoft Research New York City NY USA

ISBN: (纸本)9781450385541

We consider incentivized exploration: a version of multi-armed bandits where the choice of arms is controlled by self-interested agents, and the algorithm can only issue recommendations. The algorithm controls the flow of information, and the information asymmetry can incentivize the agents to explore. Prior work achieves optimal regret rates up to multiplicative factors that become arbitrarily large depending on the Bayesian priors, and scale exponentially in the number of arms. A more basic problem of sampling each arm once runs into similar factors. We focus on the price of incentives: the loss in performance, broadly construed, incurred for the sake of incentive-compatibility. We prove that Thompson Sampling, a standard bandit algorithm, is incentive-compatible if initialized with sufficiently many data points. The performance loss due to incentives is therefore limited to the initial rounds when these data points are collected. The problem is largely reduced to that of sample complexity: how many rounds are needed? We address this question, providing matching upper and lower bounds and instantiating them in various corollaries. Typically, the optimal sample complexity is polynomial in the number of arms and exponential in the "strength of beliefs".

关键词： sample complexity bayesian incentive-compatibility multi-armed bandits mechanism design thompson sampling incentivized exploration

来源：评论

学校读者我要写书评

暂无评论

On the sample complexity of Uncertain Linear and Bilinear Matrix Inequalities

On the Sample Complexity of Uncertain Linear and Bilinear Ma...

引用

IEEE Annual Conference on Decision and Control

作者： Mohammadreza Chamanbaz Fabrizio Dabbene Roberto Tempo Venkatakrishnan Venkataramanan Qing-Guo Wang Data Storage Institute Singapore IEIIT-CNR Torino Italy Department of Electrical and Computer Engineering National University of Singapore

ISBN: (纸本)9781467357159

In this paper, we consider uncertain linear and bilinear matrix inequalities which depend in a possibly nonlinear way on a vector of uncertain parameters. Motivated by recent results in statistical learning, we show that probabilistic guaranteed solutions can be obtained by means of randomized algorithms. In particular, we show that the Vapnik-Chevonenkis dimension (VC-dimension) of the two problems is finite, and we compute upper bounds on it. In turn, these bounds allow us to derive explicitly the sample complexity of the problems. Using these bounds, in the second part of the paper, we derive a sequential scheme, based on a sequence of optimization and validation steps. The algorithm is on the same lines of recent schemes proposed for similar problems, but improves both in terms of complexity and generality.

关键词： sample complexity Plant uncertain bilinearity Statistical learning randomized algorithms inequalities Upper bound Uncertainty Finite

来源：评论

学校读者我要写书评

暂无评论

On the sample complexity of Subspace Learning 13

On the Sample Complexity of Subspace Learning

引用

Annual Conference on Neural Information Processing Systems

作者： Alessandro Rudi Guillermo D. Canas Lorenzo Rosasco Robotics Brain and Cognitive Science Istituto Italiano di Tecnologia Massachussetss Institute of Technology Universita' degli Studi di Genova LCSL Massachusetts Institute of Technology & Istituto Italiano di Tecnologia

ISBN: (纸本)9781632660244

A large number of algorithms in machine learning, from principal component analysis (PCA), and its non-linear (kernel) extensions, to more recent spectral embedding and support estimation methods, rely on estimating a linear subspace from samples. In this paper we introduce a general formulation of this problem and derive novel learning error estimates. Our results rely on natural assumptions on the spectral properties of the covariance operator associated to the data distribution, and hold for a wide class of metrics between subspaces. As special cases, we discuss sharp error estimates for the reconstruction properties of PCA and spectral support estimation. Key to our analysis is an operator theoretic approach that has broad applicability to spectral learning methods.

关键词： Subspace principal components analysis sample complexity data distribution Passive Cutaneous Anaphylaxis Learning Metronidazole Learning methods

来源：评论

学校读者我要写书评

暂无评论

On the sample complexity of Randomized Approaches to the Analysis and Design under Uncertainty

On the Sample Complexity of Randomized Approaches to the Ana...

引用

American Control Conference

作者： T. Alamo R. Tempo A. Luque Departamento de Ingenieria de Sistemas y Automatica Universidad de Sevilla Escuela Superior de Ingenieros Camino de los Descubrimientos s/n 41092 Sevilla. Spain IEIIT-CNR Politecnico di Torino Corso Duca degli Abruzzi 24 Torino 10129 Italy

ISBN: (纸本)9781424474264

In this paper, we study the sample complexity of probabilistic methods for control of uncertain systems. In particular, we show the role of the binomial distribution for some problems involving analysis and design of robust controllers with finite families. We also address the particular case in which the design problem can be formulated as an uncertain convex optimization problem. The results of the paper provide simple explicit sample bounds to guarantee that the obtained solutions meet some pre-specified probabilistic specifications.

关键词： randomized algorithms probabilistic robustness uncertain systems sample complexity

来源：评论

学校读者我要写书评

暂无评论

ON THE sample complexity OF GRAPHICAL MODEL SELECTION FROM NON-STATIONARY sampleS

ON THE SAMPLE COMPLEXITY OF GRAPHICAL MODEL SELECTION FROM N...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Nguyen Q. Tran Alexander Jung Dept. of Computer Science Aalto University Finland

ISBN: (纸本)9781538646595

We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed samples are modeled as a zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This includes the case where observations form stationary or underspread processes. We derive a sufficient condition on the required sample size by analyzing a simple sparse neighborhood regression method.

关键词： sparsity graphical model selection neighborhood regression high-dimensional statistics sample Size sample complexity Higher statistics variance covariance matrix complexity Stochastic Processes Graphical models

来源：评论

学校读者我要写书评

暂无评论

Tight sample complexity of Large-Margin Learning 10

Tight Sample Complexity of Large-Margin Learning

引用

Annual Conference on Neural Information Processing Systems

作者： Sivan Sabato Nathan Srebro Naftali Tishby School of Computer Science & Engineering The Hebrew University Jerusalem 91904 Israel Toyota Technological Institute at Chicago Chicago IL 60637 USA

ISBN: (纸本)9781617823800

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L_2 regularization: We introduce the 7-adapted-dimension, which is a simple function of the spectrum of a distribution's covariance matrix, and show distribution-specific upper and lower bounds on the sample complexity, both governed by the 7-adapted-dimension of the source distribution. We conclude that this new quantity tightly characterizes the true sample complexity of large-margin classification. The bounds hold for a rich family of sub-Gaussian distributions.

关键词： sample complexity dimensions simple function Lower bound

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共44页 << < 5 6 7 8 9 10 11 12 13 14 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：