下载资源悬赏专区
statistical Models and Methods for Financial Markets下载
墨衍会员 · AI 创作全网分发 墨衍智能分发 通过墨衍一键同步至各平台 可同步平台 CSDN微信公众号微博知乎掘金百家号博客园抖音小红书 你的文章也可以这样分发 墨衍会员 ¥399起/年，写一次发全网
我也要 关注 + 加入社区相关下载链接：//download.csdn.net/download/taotaih/10486430?utm_source=bbsseo
相关推荐
Statistical Models and Methods for Financial Markets
This book presents statistical methods and models of importance to quantitative finance and links finance theory to market practice via statistical modeling and decision making Part I provides basic background in statistics which includes linear regression and extensions to generalized linear models and nonlinear regression multivariate analysis likelihood inference and Bayesian methods and time series analysis It also describes applications of these methods to portfolio theory and dynamic models of asset returns and their volatilities Part II presents advanced topics in quantitative finance and introduces a substantive empirical modeling approach to address the discrepancy between finance theory and market data It describes applications to option pricing interest rate markets statistical trading strategies and risk management Nonparametric regression advanced multivariate and time series methods in financial econometrics and statistical models for high frequency transactions data are also introduced in this connection The book has been developed as a textbook for courses on statistical modeling in quantitative finance in master"s level financial mathematics or engineering and computational or mathematical finance programs It is also designed for self study by quantitative analysts in the financial industry who want to learn more about the background and details of the statistical methods used by the industry It can also be used as a reference for graduate statistics and econometrics courses on regression multivariate analysis likelihood and Bayesian inference nonparametrics and time series providing concrete examples and data from financial markets to illustrate the statistical methods ">This book presents statistical methods and models of importance to quantitative finance and links finance theory to market practice via statistical modeling and decision making Part I provides basic background in statistics which includes linear regression and extensions to generalized linear mode [更多]
视觉特征-自监督-同源不同crop视图一致性【2023-04】：DINOv2（无监督学习鲁棒视觉特征）【12 亿张互不重复的图像】【判别式自监督方法】【交叉熵损失+iBOT损失】
近期，自然语言处理领域在大量数据上进行模型 Pretraining 取得的突破，为计算机视觉中类似Foundation Model 的发展开辟了道路。这些模型能够生成通用视觉特征，即无需微调即可跨图像分布和任务发挥作用的特征，从而大幅简化图像在任何系统中的使用。本研究表明，现有的 Pretraining 方法，尤其是自监督方法，如果在来自多样化来源的充足精选数据上进行训练，便能够产生此类特征。我们重新审视了现有方法，并结合不同技术，从数据规模和模型规模两方面扩展我们的 Pretraining。
视觉特征-自监督-掩码特征预测【2024-04】：V-JEPA【潜空间】【≈90%多块时空掩码】【上下文目标块预测】【特征空间预测≠像素重建】【EMA目标编码器+停梯度】
Adrien Bardes 1,2,3, Quentin Garrido 1,4, Jean Ponce 3,5,6, Xinlei Chen 1, Michael Rabbat 1, Yann LeCun 1,5,6, Mahmoud Assran 1,†, Nicolas Ballas 1,† 1 FAIR at Meta, 2 Inria, 3 École normale supérieure, CNRS, PSL Research University, 4 Univ. Gustave Eiffel
视觉特征-自监督-对比学习：SimCLR（在潜空间用对比损失最大化同一样本经不同数据增强所得视图间的一致性来学习表示）【Loss：对比损失函数】【同批次非同源样本作为负样本】【2020-02】
Abstract摘要本文提出了SimCLR：一个用于视觉表征对比学习的简单框架。我们简化了近期提出的对比式自监督学习算法，无需专门的架构或记忆库。为了理解是什么使对比预测任务能够学习到有用的表征，我们系统地研究了该框架的主要组成部分。我们表明：(1)数据增强的组合在定义有效预测任务中起着关键作用；(2)在表征与对比损失之间引入可学习的非线性变换，可显著提升所学习表征的质量；(3)与监督学习相比，对比学习受益于更大的批量大小和更多的训练步骤。
statistical Models and Methods for Financial Markets
对于学习商务统计模型非常有帮助，非常适合商科master们学习
