检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Viktor Bengs Eyke Hüllermeier Willem Waegeman Institute of Informatics University of Munich (LMU) Institute of Informatics University of Munich (LMU) and Munich Center for Machine Learning Department of Data Analysis and Mathematical Modeling Ghent University

ISBN: (纸本)9781713871088

Uncertainty quantification has received increasing attention in machine learning in the recent past. In particular, a distinction between aleatoric and epistemic uncertainty has been found useful in this regard. The latter refers to the learner's (lack of) knowledge and appears to be especially difficult to measure and quantify. In this paper, we analyse a recent proposal based on the idea of a second-order learner, which yields predictions in the form of distributions over probability distributions. While standard (first-order) learners can be trained to predict accurate probabilities, namely by minimising suitable loss functions on sample data, we show that loss minimisation does not work for second-order predictors: The loss functions proposed for inducing such predictors do not incentivise the learner to represent its epistemic uncertainty in a faithful way.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPR-Net: constructing a non-equilibrium potential landscape via a variational force projection formulation

引用

National Science Review 2024年第7期11卷 135-147页

作者： Yue Zhao Wei Zhang Tiejun Li Center for Data Science Peking University Zuse Institute Berlin Department of Mathematics and Computer Science Freie Universit?t Berlin Laboratory of Mathematics and Applied Mathematics(LMAM)and School of Mathematical Sciences Peking University Center for Machine Learning Research Peking University

We present EPR-Net, a novel and effective deep learning approach that tackles a crucial challenge in biophysics: constructing potential landscapes for high-dimensional non-equilibrium steady-state ***-Net leverages a nice mathematical fact that the desired negative potential gradient is simply the orthogonal projection of the driving force of the underlying dynamics in a weighted inner-product ***, our loss function has an intimate connection with the steady entropy production rate(EPR),enabling simultaneous landscape construction and EPR estimation. We introduce an enhanced learning strategy for systems with small noise, and extend our framework to include dimensionality reduction and the state-dependent diffusion coefficient case in a unified fashion. Comparative evaluations on benchmark problems demonstrate the superior accuracy, effectiveness and robustness of EPR-Net compared to existing methods. We apply our approach to challenging biophysical problems, such as an eight-dimensional(8D)limit cycle and a 52D multi-stability problem, which provide accurate solutions and interesting insights on constructed landscapes. With its versatility and power, EPR-Net offers a promising solution for diverse landscape construction problems in biophysics.

关键词： high-dimensional potential landscape non-equilibrium system entropy production rate dimensionality reduction deep learning

来源：评论

学校读者我要写书评

暂无评论

Method for Finding an Investment Strategy in the Case of a Sparse Covariance Matrix

Method for Finding an Investment Strategy in the Case of a S...

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Victor Gorelik Tatiana Zolotova Department of Simulation Systems and Operations Research Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences Moscow Russia Department of Data Analysis and Machine Learning Financial University under the Government of the Russian Federation Moscow Russia

An optimality principle is proposed for making investment decisions based on efficiency and risk assessments with a sparse covariance matrix. The method is implemented as a program with a graphical interface and demon... 详细信息

ISBN: (数字)9798350375718

ISBN: (纸本)9798350375725

关键词： Large-scale systems Sparse matrices Risk management Covariance matrices Stock markets Portfolios Investment

来源：评论

学校读者我要写书评

暂无评论

Investor Risk Profile Determination Model

Investor Risk Profile Determination Model

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Victor Gorelik Tatiana Zolotova Department of Simulation Systems and Operations Research Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia Department of Data Analysis and Machine Learning Financial University Under the Government of the Russian Federation Moscow Russia

An assessment of the investor’s risk profile is proposed as a risk coefficient in a model with a linear convolution of expected return and variance. The value of the risk coefficient is found from solving the optimization problem of the model with a limitation on profitability. The proposed method is implemented in the form of a software package using the example of the stock market.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Transformers Get Rich: Approximation and Dynamics analysis

arXiv

引用

arXiv 2024年

作者： Wang, Mingze Yu, Ruoxi Weinan, E. Wu, Lei School of Mathematical Sciences Peking University China School of Mathematical Sciences Center for Machine Learning Research AI for Science Institute Peking University China Center for Data Science Peking University China School of Mathematical Sciences Center for Machine Learning Research Peking University China

Transformers have demonstrated exceptional in-context learning capabilities, yet the theoretical understanding of the underlying mechanisms remains limited. A recent work (Elhage et al., 2021) identified a "rich" in-context mechanism known as induction head, contrasting with "lazy" n-gram models that overlook long-range dependencies. In this work, we provide both approximation and dynamics analyses of how transformers implement induction heads. In the approximation analysis, we formalize both standard and generalized induction head mechanisms, and examine how transformers can efficiently implement them, with an emphasis on the distinct role of each transformer submodule. For the dynamics analysis, we study the training dynamics on a synthetic mixed target, composed of a 4-gram and an in-context 2-gram component. This controlled setting allows us to precisely characterize the entire training process and uncover an abrupt transition from lazy (4-gram) to rich (induction head) mechanisms as training progresses. Copyright © 2024, The Authors. All rights reserved.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Clinical-Guided Binocular Fusion Framework for Predicting New-Onset Hypertension Over a Four-Year Period

Multi-Scale Clinical-Guided Binocular Fusion Framework for P...

引用

IEEE International Symposium on Biomedical Imaging

作者： Haoshen Li Zifan Chen Jie Zhao Heyun Chen Hexin Dong Mingze Yuan Bin Dong Li Zhang Center for Data Science Peking University China National Engineering Laboratory for Big Data Analysis and Applications Peking University China Peking University Changsha Institute for Computing and Digital Economy China Beijing International Center for Mathematical Research Peking University China Center for Machine Learning Research Peking University China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Hypertension is a major global health concern, linked to various cardiovascular diseases and associated with distinct ocular manifestations. While recent advances in artificial intelligence have enabled accurate diagnosis of current hypertension through fundus images, predicting the future onset of hypertension remains an uncharted domain. In this study, we introduce the multi-scale clinical-guided binocular fusion framework (MCBO), designed to predict the likelihood of developing hypertension within the next four years. MCBO uniquely integrates left and right fundus images and clinical data, utilizing a shared-weight multi-stage Transformer-based encoder. Our multi-scale clinical-guided module (MCM) ensures image feature extraction is clinically contextualized based on clinical information, and our binocular fusion module (BFM) fuses binocular information. Comparative performance against seven baseline models establishes MCBO’s supremacy, with improvements of 6.7% in Area Under Curve (AUC), 6.9% in Accuracy (ACC), 5.1% in Sensitivity (SEN) and 5.5% in Specificity (SPE). This approach offers a promising avenue for proactive hypertension management, underscoring the potential of integrating Deep learning with clinical data for enhanced healthcare outcomes. Our code is available at https://***/HaoshenLi/MCBO.

关键词： Hypertension Deep learning Accuracy Sensitivity Codes Fuses Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Object Segmentation Tracking from Generic Video Cues

Object Segmentation Tracking from Generic Video Cues

引用

International Conference on Pattern Recognition

作者： Amirhossein Kardoost Sabine Müller Joachim Weickert Margret Keuper Data and Web Science Group University of Mannheim Mannheim Germany Fraunhofer Center Machine Learning Germany Mathematical Image Analysis Group Saarland University Saarbrücken Germany

We propose a light-weight variational framework for online tracking of object segmentations in videos based on optical flow and image boundaries. While high-end computer vision methods on this task rely on sequence specific training of dedicated CNN architectures, we show the potential of a variational model, based on generic video information from motion and color. Such cues are usually required for tasks such as robot navigation or grasp estimation. We leverage them directly for video object segmentation and thus provide accurate segmentations at potentially very low extra cost. Our simple method can provide competitive results compared to the costly CNN-based methods with parameter tuning. Furthermore, we show that our approach can be combined with state-of-the-art CNN-based segmentations in order to improve over their respective results. We evaluate our method on the datasets DAVIS16,17 and SegTrack v2.

关键词： Training Navigation Annotations Video sequences Estimation Object segmentation Task analysis

来源：评论

学校读者我要写书评

暂无评论

Revealing excited states of rotational Bose-Einstein condensates

引用

The Innovation 2024年第1期5卷 41-48页

作者： Jianyuan Yin Zhen Huang Yongyong Cai Qiang Du Lei Zhang School of Mathematical Sciences Laboratory of Mathematics and Applied MathematicsPeking UniversityBeijing 100871China Department of Mathematics National University of SingaporeSingapore 119076Singapore Department of Mathematics University of CaliforniaBerkeleyBerkeleyCA 94720USA School of Mathematical Sciences Beijing Normal UniversityBeijing 100875China Department of Applied Physics and Applied Mathematics and Data Science Institute Columbia UniversityNew YorkNY 10027USA Beijing International Center for Mathematical Research Center for Quantitative BiologyCenter for Machine Learning ResearchPeking UniversityBeijing 100871China

Rotational Bose-Einstein condensates can exhibit quantized vortices as topological *** this study,the ground and excited states of the rotational Bose-Einstein condensates are systematically studied by calculating the stationary points of the Gross-Pitaevskii energy *** excited states and their connections at different rotational frequencies are revealed in solution landscapes constructed with the constrained high-index saddle dynamics *** excitation mechanisms are identified:vortex addition,rearrangement,merging,and *** demonstrate changes in the ground state with increasing rotational frequencies and decipher the evolution of the stability of ground states.

关键词： method rotational excited

来源：评论

学校读者我要写书评

暂无评论

ENHANCING ZEROTH-ORDER FINE-TUNING FOR LANGUAGE MODELS WITH LOW-RANK STRUCTURES

arXiv

引用

arXiv 2024年

作者： Chen, Yiming Zhang, Yuan Cao, Liyuan Yuan, Kun Wen, Zaiwen Beijing International Center for Mathematical Research Peking University Beijing China Center for Data Science Peking University Beijing China Center for Machine Learning Research Peking University Beijing China

Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting large language models (LLMs) for downstream applications. However, traditional first-order (FO) fine-tuning algorithms incur substantial memory overhead due to the need to store activation values for back-propagation during gradient computation, particularly in long-context fine-tuning tasks. Zeroth-order (ZO) algorithms offer a promising alternative by approximating gradients using finite differences of function values, thus eliminating the need for activation storage. Nevertheless, existing ZO methods struggle to capture the low-rank gradient structure common in LLM fine-tuning, leading to suboptimal performance. This paper proposes a low-rank ZO gradient estimator and introduces a novel low-rank ZO algorithm (LOZO) that effectively captures this structure in LLMs. We provide convergence guarantees for LOZO by framing it as a subspace optimization method. Additionally, its low-rank nature enables LOZO to integrate with momentum techniques while incurring negligible extra memory costs. Extensive experiments across various model sizes and downstream tasks demonstrate that LOZO and its momentum-based variant outperform existing ZO methods and closely approach the performance of FO algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LimeSoDa: A dataset Collection for Benchmarking of machine learning Regressors in Digital Soil Mapping

arXiv

引用

arXiv 2025年

作者： Schmidinger, Jonas Vogel, Sebastian Barkov, Viacheslav Pham, Anh-Duy Gebbers, Robin Tavakoli, Hamed Correa, Jose Tavares, Tiago R. Filippi, Patrick Jones, Edward J. Lukas, Vojtech Boenecke, Eric Ruehlmann, Joerg Schroeter, Ingmar Kramer, Eckart Paetzold, Stefan Kodaira, Masakazu Wadoux, Alexandre M.J.-C. Bragazza, Luca Metzger, Konrad Huang, Jingyi Valente, Domingos S.M. Safanelli, Jose L. Bottega, Eduardo L. Dalmolin, Ricardo S.D. Farkas, Csilla Steiger, Alexander Horst, Taciara Z. Ramirez-Lopez, Leonardo Scholten, Thomas Stumpf, Felix Rosso, Pablo Costa, Marcelo M. Zandonadi, Rodrigo S. Wetterlind, Johanna Atzmueller, Martin Osnabrück University Joint Lab Artificial Intelligence and Data Science Osnabrück Germany Department of Agromechatronics Potsdam Germany Piracicaba Brazil The University of Sydney Sydney Institute of Agriculture Sydney Australia Mendel University in Brno Department of Agrosystems and Bioclimatology Brno Czech Republic Leibniz Institute of Vegetable and Ornamental Crops Next Generation Horticultural Systems Grossbeeren Germany Eberswalde University for Sustainable Development Landscape Management and Nature Conservation Eberswalde Germany Soil Science and Soil Ecology Bonn Germany Tokyo University of Agriculture and Technology Institute of Agriculture Tokyo Japan LISAH Univ. Montpellier AgroParisTech INRAE IRD L'Institut Agro Montpellier France Agroscope Field-Crop Systems and Plant Nutrition Nyon Switzerland University of Wisconsin-Madison Department of Soil Science Madison United States Federal University of Viçosa Department of Agricultural Engineering Viçosa Brazil Woodwell Climate Research Center Falmouth United States Academic Coordination Santa Maria Brazil Soil Department Santa Maria Brazil Division of Environment and Natural Resources Aas Norway University of Rostock Chair of Geodesy and Geoinformatics Rostock Germany Federal Technological University of Paraná Dois Vizinhos Brazil BÜCHI Labortechnik AG Data Science Department Flawil Switzerland Imperial College London Imperial College Business School London United Kingdom University of Tübingen Department of Geosciences Tübingen Germany University of Tübingen DFG Cluster of Excellence Machine Learning for Science’ Germany Bern University of Applied Sciences Competence Center for Soils Zollikofen Switzerland Simulation and Data Science Müncheberg Germany Federal University of Jataí Institute of Agricultural Sciences Jatai Brazil Federal University of Mato Grosso Instute of Agricultural and Environmental Scinces Sinop Brazil Department of Soil and Environment Skara

Digital soil mapping (DSM) relies on a broad pool of statistical methods, yet determining the optimal method for a given context remains challenging and contentious. Benchmarking studies on multiple datasets are needed to reveal strengths and limitations of commonly used methods. Existing DSM studies usually rely on a single dataset with restricted access, leading to incomplete and potentially misleading conclusions. To address these issues, we introduce an open-access dataset collection called Precision Liming Soil datasets (LimeSoDa). LimeSoDa consists of 31 field- and farm-scale datasets from various countries. Each dataset has three target soil properties: (1) soil organic matter or soil organic carbon, (2) clay content and (3) pH, alongside a set of features. Features are dataset-specific and were obtained by optical spectroscopy, proximal- and remote soil sensing. All datasets were aligned to a tabular format and are ready-to-use for modeling. We demonstrated the use of LimeSoDa for benchmarking by comparing the predictive performance of four learning algorithms across all datasets. This comparison included multiple linear regression (MLR), support vector regression (SVR), categorical boosting (CatBoost) and random forest (RF). The results showed that although no single algorithm was universally superior, certain algorithms performed better in specific contexts. MLR and SVR performed better on high-dimensional spectral datasets, likely due to better compatibility with principal components. In contrast, CatBoost and RF exhibited considerably better performances when applied to datasets with a moderate number ( © 2025, CC BY-SA.

关键词： Adversarial machine learning

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：