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

317 篇 期刊文献
162 篇 会议

馆藏范围

479 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

361 篇 工学
- 314 篇 计算机科学与技术...
- 266 篇 软件工程
- 59 篇 信息与通信工程
- 50 篇 生物工程
- 27 篇 化学工程与技术
- 25 篇 控制科学与工程
- 17 篇 光学工程
- 14 篇 机械工程
- 12 篇 电气工程
- 9 篇 建筑学
- 9 篇 土木工程
- 9 篇 生物医学工程（可授...
- 9 篇 网络空间安全
- 6 篇 动力工程及工程热...
- 6 篇 电子科学与技术（可...
- 6 篇 安全科学与工程
- 5 篇 材料科学与工程（可...
190 篇 理学
- 109 篇 数学
- 54 篇 生物学
- 39 篇 统计学（可授理学、...
- 32 篇 物理学
- 30 篇 化学
- 21 篇 系统科学
80 篇 管理学
- 55 篇 图书情报与档案管...
- 31 篇 管理科学与工程(可...
24 篇 法学
- 24 篇 社会学
7 篇 教育学
- 7 篇 教育学
7 篇 文学
- 6 篇 中国语言文学
- 6 篇 外国语言文学
4 篇 经济学
- 4 篇 应用经济学
4 篇 医学
1 篇 农学
1 篇 艺术学

主题

21 篇 semantics
17 篇 recommender syst...
17 篇 computational li...
14 篇 machine learning
12 篇 graph neural net...
10 篇 knowledge graph
10 篇 diffusion
9 篇 reinforcement le...
9 篇 distillation
9 篇 benchmarking
9 篇 forecasting
6 篇 generative adver...
6 篇 search engines
5 篇 contrastive lear...
5 篇 tensors
4 篇 surveys
4 篇 object detection
4 篇 user profile
4 篇 deep learning
4 篇 large dataset

机构

336 篇 beijing key labo...
315 篇 gaoling school o...
104 篇 school of inform...
24 篇 tsinghua univers...
23 篇 beijing academy ...
20 篇 beijing key labo...
20 篇 gaoling school o...
17 篇 beijing key labo...
17 篇 gaoling school o...
15 篇 gaoling school o...
14 篇 diro université ...
14 篇 alibaba group
12 篇 dept. of comp. s...
11 篇 department of co...
10 篇 university of ch...
9 篇 nlp group dcst i...
9 篇 dept. of comp. s...
9 篇 key laboratory o...
9 篇 quan cheng labor...
8 篇 school of softwa...

作者

158 篇 wen ji-rong
104 篇 zhao wayne xin
46 篇 li chongxuan
40 篇 lu zhiwu
34 篇 zhou kun
31 篇 huang wenbing
30 篇 su bing
28 篇 zhu jun
26 篇 chen xu
25 篇 xu hongteng
25 篇 lin yankai
22 篇 liu yang
20 篇 bao fan
20 篇 li junyi
19 篇 ji-rong wen
18 篇 tang tianyi
17 篇 dou zhicheng
16 篇 liu yong
15 篇 zhou jie
15 篇 yong liu

语言

443 篇 英文
33 篇 其他
3 篇 中文

检索条件"机构=Beijing Key Laboratory of Big-Data Management and Analysis Methods"

共 479 条记录，以下是31-40 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：

High Probability analysis for Non-Convex Stochastic Optimization with Clipping 26

High Probability Analysis for Non-Convex Stochastic Optimiza...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Li, Shaojie Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9781643684369

Gradient clipping is a commonly used technique to stabilize the training process of neural networks. A growing body of studies has shown that gradient clipping is a promising technique for dealing with the heavy-tailed behavior that emerged in stochastic optimization as well. While gradient clipping is significant, its theoretical guarantees are scarce. Most theoretical guarantees only provide an in-expectation analysis and only focus on optimization performance. In this paper, we provide high probability analysis in the non-convex setting and derive the optimization bound and the generalization bound simultaneously for popular stochastic optimization algorithms with gradient clipping, including stochastic gradient descent and its variants of momentum and adaptive stepsizes. With the gradient clipping, we study a heavy-tailed assumption that the gradients only have bounded α-th moments for some α ∈ (1, 2], which is much weaker than the standard bounded second-moment assumption. Overall, our study provides a relatively complete picture for the theoretical guarantee of stochastic optimization algorithms with clipping. © 2023 The Authors.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

TEMPORAL ALIGNMENT PREDICTION FOR SUPERVISED REPRESENTATION LEARNING AND FEW-SHOT SEQUENCE CLASSIFICATION 10

TEMPORAL ALIGNMENT PREDICTION FOR SUPERVISED REPRESENTATION ...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Su, Bing Wen, Ji-Rong Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China

Explainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances. Most sequence alignment methods infer the optimal alignment by solving an optimization problem under pre-defined feasible alignment constraints, which not only is time-consuming, but also makes end-to-end sequence learning intractable. In this paper, we propose a learnable sequence distance called Temporal Alignment Prediction (TAP). TAP employs a lightweight convolutional neural network to directly predict the optimal alignment between two sequences, so that only straightforward calculations are required and no optimization is involved in inference. TAP can be applied in different distance-based machine learning tasks. For supervised sequence representation learning, we show that TAP trained with various metric learning losses achieves completive performances with much faster inference speed. For few-shot action classification, we apply TAP as the distance measure in the metric learning-based episode-training paradigm. This simple strategy achieves comparable results with state-of-the-art few-shot action recognition methods. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Perfect Alignment May be Poisonous to Graph Contrastive Learning 41

Perfect Alignment May be Poisonous to Graph Contrastive Lear...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jingyu Tang, Huayi Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones. However, few of researchers have focused on the inner law behind specific augmentations used in graph-based learning. What kind of augmentation will help downstream performance, how does contrastive learning actually influence downstream tasks, and why the magnitude of augmentation matters so much? This paper seeks to address these questions by establishing a connection between augmentation and downstream performance. Our findings reveal that GCL contributes to downstream tasks mainly by separating different classes rather than gathering nodes of the same class. So perfect alignment and augmentation overlap which draw all intra-class samples the same can not fully explain the success of contrastive learning. Therefore, in order to understand how augmentation aids the contrastive learning process, we conduct further investigations into the generalization, finding that perfect alignment that draw positive pair the same could help contrastive loss but is poisonous to generalization, as a result, perfect alignment may not lead to best downstream performance, so specifically designed augmentation is needed to achieve appropriate alignment performance and improve downstream accuracy. We further analyse the result by information theory and graph spectrum theory and propose two simple but effective methods to verify the theories. The two methods could be easily applied to various GCL algorithms and extensive experiments are conducted to prove its effectiveness. The code is available at https://***/somebodyhh1/GRACEIS. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

GENERALIZATION BOUNDS FOR FEDERATED LEARNING: FAST RATES, UNPARTICIPATING CLIENTS AND UNBOUNDED LOSSES 11

GENERALIZATION BOUNDS FOR FEDERATED LEARNING: FAST RATES, UN...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Hu, Xiaolin Li, Shaojie Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

In federated learning, the underlying data distributions may be different across clients. This paper provides a theoretical analysis of generalization error of federated learning, which captures both heterogeneity and relatedness of the distributions. In particular, we assume that the heterogeneous distributions are sampled from a meta-distribution. In this two-level distribution framework, we characterize the generalization error not only for clients participating in the training but also for unparticipating clients. We first show that the generalization error for unparticipating clients can be bounded by participating generalization error and participating gap caused by clients' sampling. We further establish fast learning bounds of order (Equation presented) for unparticipating clients, where m is the number of clients and n is the sample size at each client. To our knowledge, the obtained fast bounds are state-of-the-art in the two-level distribution framework. Moreover, previous theoretical results mostly require the loss function to be bounded. We derive convergence bounds of order (Equation presented) under unbounded assumptions, including sub-exponential and sub-Weibull losses. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Concentration Inequalities for General Functions of Heavy-Tailed Random Variables 41

Concentration Inequalities for General Functions of Heavy-Ta...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Shaojie Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Concentration inequalities play an essential role in the study of machine learning and high dimensional statistics. In this paper, we obtain unbounded analogues of the popular bounded difference inequality for functions of independent random variables with heavy-tailed distributions. The main results provide a general framework applicable to all heavy-tailed distributions with finite variance. To illustrate the strength of our results, we present applications to sub-exponential tails, sub-Weibull tails, and heavier polynomially decaying tails. Applied to some standard problems in statistical learning theory (vector valued concentration, Rademacher complexity, and algorithmic stability), we show that these inequalities allow an extension of existing results to heavy-tailed distributions up to finite variance. Copyright 2024 by the author(s)

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Robust Recommendation with Adversarial Gaussian data Augmentation 23

Robust Recommendation with Adversarial Gaussian Data Augment...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Zhenlei Chen, Xu Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Gaoling School of Artifcial Intelligence Renmin University of China Beijing China

ISBN: (纸本)9781450394161

Recommender system holds the promise of accurately understanding and estimating the user preferences. However, due to the extremely sparse user-item interactions, the learned recommender models can be less robust and sensitive to the highly dynamic user preferences and easily changed recommendation environments. To alleviate this problem, in this paper, we propose a simple yet effective robust recommender framework by generating additional samples from the Gaussian distributions. In specific, we design two types of data augmentation strategies. For the first one, we directly produce the data based on the original samples, where we simulate the generation process in the latent space. For the second one, we firstly change the original samples towards the direction of maximizing the loss function, and then produce the data based on the altered samples to make more effective explorations. Based on both of the above strategies, we leverage adversarial training to optimize the recommender model with the generated data which can achieve the largest losses. In addition, we theoretically analyze our framework, and find that the above two data augmentation strategies equal to impose a gradient based regularization on the original recommender models. We conduct extensive experiments based on six real-world datasets to demonstrate the effectiveness of our framework. © 2023 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses 41

Algorithmic Stability Unleashed: Generalization Bounds with ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Shaojie Zhu, Bowei Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

One of the central problems of statistical learning theory is quantifying the generalization ability of learning algorithms within a probabilistic framework. Algorithmic stability is a powerful tool for deriving generalization bounds, however, it typically builds on a critical assumption that losses are bounded. In this paper, we relax this condition to unbounded loss functions with subweibull diameter. This gives new generalization bounds for algorithmic stability and also includes existing results of subgaussian and subexponential diameters as specific cases. Furthermore, we provide a refined stability analysis by developing generalization bounds which can be √n-times faster than the previous results, where n is the sample size. Our main technical contribution is general concentration inequalities for subweibull random variables, which may be of independent interest. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepInsight: Multi-task multi-scale deep learning for mental disorder diagnosis 29

DeepInsight: Multi-task multi-scale deep learning for mental...

引用

29th British Machine Vision Conference, BMVC 2018

作者： Ding, Mingyu Huo, Yuqi Hu, Jun Lu, Zhiwu School of Information Renmin University of China Beijing100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing100872 China

We propose a novel deep learning approach, called DeepInsight, to quick diagnosis of autism spectrum disorder (ASD) and major depressive disorder (MDD). Our approach is motivated by recent advances in artificial intelligence (AI) for healthcare. In particular, researchers have found distinct differences between facial characteristics of children with ASD and those of typically developing children. Based upon these findings, we choose to explore deep learning in extracting discriminative facial features. However, for ASD diagnosis, the labelled data are far from sufficient for training a deep learning model. Therefore, by considering the two typical mental disorders (i.e. ASD and MDD) together, we develop a multi-task deep learning model to augment the labelled data for each diagnosis task. Moreover, we also induce multi-scale combination into the proposed model to learn more discriminative facial features. Experimental results demonstrate the effectiveness and efficiency of our approach to mental disorder diagnosis. © 2018. The copyright of this document resides with its authors.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Effective Ancient Chinese Translation: dataset, Model, and Evaluation 12th

Towards Effective Ancient Chinese Translation: Dataset, Mode...

引用

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Guo, Geyang Yang, Jiarong Lu, Fengyuan Qin, Jiaxin Tang, Tianyi Zhao, Wayne Xin Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9783031446955

Interpreting ancient Chinese has been the key to comprehending vast Chinese literature, tradition, and civilization. In this paper, we propose Erya for ancient Chinese translation. From a dataset perspective, we collect, clean, and classify ancient Chinese materials from various sources, forming the most extensive ancient Chinese resource to date. From a model perspective, we devise Erya training method oriented towards ancient Chinese. We design two jointly-working tasks: disyllabic aligned substitution (DAS) and dual masked language model (DMLM). From an evaluation perspective, we build a benchmark to judge ancient Chinese translation quality in different scenarios and evaluate the ancient Chinese translation capacities of various existing models. Our model exhibits remarkable zero-shot performance across five domains, with over +12.0 BLEU against GPT-3.5 models and better human evaluation results than ERNIE Bot. Subsequent fine-tuning further shows the superior transfer capability of Erya model with +6.2 BLEU gain. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

HIGH PROBABILITY GENERALIZATION BOUNDS WITH FAST RATES FOR MINIMAX PROBLEMS 10

HIGH PROBABILITY GENERALIZATION BOUNDS WITH FAST RATES FOR M...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Li, Shaojie Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Minimax problems are receiving an increasing amount of attention in a wide range of applications in machine learning (ML), for instance, reinforcement learning, robust optimization, adversarial learning, and distributed computing, to mention but a few. Current studies focus on the fundamental understanding of general minimax problems with an emphasis on convergence behavior. As a comparison, there is far less work to study the generalization performance. Additionally, existing generalization bounds are almost all derived in expectation, and the high probability bounds are all presented in the slow order O(1/√n), where n is the sample size. In this paper, we provide improved generalization analyses and obtain sharper high probability generalization bounds for most existing generalization measures of minimax problems. We then use the improved learning bounds to establish high probability generalization bounds with fast rates for classical empirical saddle point (ESP) solution and several popular gradient-based optimization algorithms, including gradient descent ascent (GDA), stochastic gradient descent ascent (SGDA), proximal point method (PPM), extra-gradient (EG), and optimistic gradient descent ascent (OGDA). In summary, we provide a systematical analysis of sharper generalization bounds of minimax problems. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Reinforcement learning

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48页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：