add references!

datawhalechina · Sep 19, 2024 · 83adf21 · 83adf21
1 parent 2584709
commit 83adf21
Show file tree

Hide file tree

Showing 16 changed files with 84 additions and 35 deletions.
diff --git a/README.md b/README.md
@@ -32,19 +32,19 @@ https://github.com/datawhalechina/key-book/releases
 
 ### 目录
 
-- 第0章 [绪论](https://datawhalechina.github.io/key-book/#/chapter0/chapter0)
-- 第1章 [预备知识](https://datawhalechina.github.io/key-book/#/chapter1/chapter1)
-- 第2章 [可学性](https://datawhalechina.github.io/key-book/#/chapter2/chapter2)
-- 第3章 [复杂度](https://datawhalechina.github.io/key-book/#/chapter3/chapter3)
-- 第4章 [泛化界](https://datawhalechina.github.io/key-book/#/chapter4/chapter4)
-- 第5章 [稳定性](https://datawhalechina.github.io/key-book/#/chapter5/chapter5)
-- 第6章 [一致性](https://datawhalechina.github.io/key-book/#/chapter6/chapter6)
-- 第7章 [收敛率](https://datawhalechina.github.io/key-book/#/chapter7/chapter7)
-- 第8章 [遗憾界](https://datawhalechina.github.io/key-book/#/chapter8/chapter8)
+- 第0章 [绪论](https://datawhalechina.github.io/key-book/#/chapter0)
+- 第1章 [预备知识](https://datawhalechina.github.io/key-book/#/chapter1)
+- 第2章 [可学性](https://datawhalechina.github.io/key-book/#/chapter2)
+- 第3章 [复杂度](https://datawhalechina.github.io/key-book/#/chapter3)
+- 第4章 [泛化界](https://datawhalechina.github.io/key-book/#/chapter4)
+- 第5章 [稳定性](https://datawhalechina.github.io/key-book/#/chapter5)
+- 第6章 [一致性](https://datawhalechina.github.io/key-book/#/chapter6)
+- 第7章 [收敛率](https://datawhalechina.github.io/key-book/#/chapter7)
+- 第8章 [遗憾界](https://datawhalechina.github.io/key-book/#/chapter8)
 
 ### 选用的《机器学习理论导引》版本
 
-<center><img src="docs/images/mlt.jpg" width="300" height= "300"></center>
+<center><img src="docs/images/original_book.jpg" width="300" height= "300"></center>
 
 > 版次：2020年6月第1版<br>
 
@@ -61,7 +61,7 @@ https://github.com/datawhalechina/key-book/releases
 ## 关注我们
 <div align=center>
 <p>扫描下方二维码，或关注公众号「Datawhale」，然后回复关键词“钥匙书”，即可加入“钥匙书读者交流群”</p>
-<img src="docs/images/qr.jpeg" width="300" height= "300">
+<img src="docs/images/qr_code.jpg" width="300" height= "300">
 <p>或者加入QQ群：704768061</p>
 </div>
 

diff --git a/docs/README.md b/docs/README.md
@@ -32,19 +32,19 @@ https://github.com/datawhalechina/key-book/releases
 
 ### 目录
 
-- 第0章 [绪论](https://datawhalechina.github.io/key-book/#/chapter0/chapter0)
-- 第1章 [预备知识](https://datawhalechina.github.io/key-book/#/chapter1/chapter1)
-- 第2章 [可学性](https://datawhalechina.github.io/key-book/#/chapter2/chapter2)
-- 第3章 [复杂度](https://datawhalechina.github.io/key-book/#/chapter3/chapter3)
-- 第4章 [泛化界](https://datawhalechina.github.io/key-book/#/chapter4/chapter4)
-- 第5章 [稳定性](https://datawhalechina.github.io/key-book/#/chapter5/chapter5)
-- 第6章 [一致性](https://datawhalechina.github.io/key-book/#/chapter6/chapter6)
-- 第7章 [收敛率](https://datawhalechina.github.io/key-book/#/chapter7/chapter7)
-- 第8章 [遗憾界](https://datawhalechina.github.io/key-book/#/chapter8/chapter8)
+- 第0章 [绪论](https://datawhalechina.github.io/key-book/#/chapter0)
+- 第1章 [预备知识](https://datawhalechina.github.io/key-book/#/chapter1)
+- 第2章 [可学性](https://datawhalechina.github.io/key-book/#/chapter2)
+- 第3章 [复杂度](https://datawhalechina.github.io/key-book/#/chapter3)
+- 第4章 [泛化界](https://datawhalechina.github.io/key-book/#/chapter4)
+- 第5章 [稳定性](https://datawhalechina.github.io/key-book/#/chapter5)
+- 第6章 [一致性](https://datawhalechina.github.io/key-book/#/chapter6)
+- 第7章 [收敛率](https://datawhalechina.github.io/key-book/#/chapter7)
+- 第8章 [遗憾界](https://datawhalechina.github.io/key-book/#/chapter8)
 
 ### 选用的《机器学习理论导引》版本
 
-<center><img src="res/mlt.jpg" width="300" height= "300"></center>
+<center><img src="res/original_book.jpg" width="300" height= "300"></center>
 
 > 版次：2020年6月第1版<br>
 
@@ -61,7 +61,7 @@ https://github.com/datawhalechina/key-book/releases
 ## 关注我们
 <div align=center>
 <p>扫描下方二维码，或关注公众号「Datawhale」，然后回复关键词“钥匙书”，即可加入“钥匙书读者交流群”</p>
-<img src="res/qr.jpeg" width="300" height= "300">
+<img src="res/qr_code.jpg" width="300" height= "300">
 <p>或者加入QQ群：704768061</p>
 </div>
 

diff --git a/docs/_sidebar.md b/docs/_sidebar.md
@@ -1,10 +1,10 @@
-- [第0章 序言](chapter0/chapter0.md)
-- [第1章 预备知识](chapter1/chapter1.md)
-- [第2章 可学性](chapter2/chapter2.md)
-- [第3章 复杂度](chapter3/chapter3.md)
-- [第4章 泛化界](chapter4/chapter4.md)
-- [第5章 稳定性](chapter5/chapter5.md)
-- [第6章 一致性](chapter6/chapter6.md)
-- [第7章 收敛率](chapter7/chapter7.md)
-- [第8章 遗憾界](chapter8/chapter8.md) 
-
+- [第0章 序言](chapter0.md)
+- [第1章 预备知识](chapter1.md)
+- [第2章 可学性](chapter2.md)
+- [第3章 复杂度](chapter3.md)
+- [第4章 泛化界](chapter4.md)
+- [第5章 稳定性](chapter5.md)
+- [第6章 一致性](chapter6.md)
+- [第7章 收敛率](chapter7.md)
+- [第8章 遗憾界](chapter8.md) 
+- [参考文献](references.md) 
diff --git a/docs/chapter0/chapter0.md → docs/chapter0.md b/docs/chapter0/chapter0.md → docs/chapter0.md
diff --git a/docs/chapter1/chapter1.md → docs/chapter1.md b/docs/chapter1/chapter1.md → docs/chapter1.md
diff --git a/docs/chapter2/chapter2.md → docs/chapter2.md b/docs/chapter2/chapter2.md → docs/chapter2.md
@@ -42,7 +42,7 @@ $$
 
 虽然这种理解适用于机器学习，但我们必须注意，对于深度学习，需要进一步的考虑。例如双下降现象与传统机器学习理论相矛盾，后者认为增加模型大小和数据量通常会提高模型的泛化性能。
 
-![double_descent](../images/double_descent.png)
+![double_descent](images/double_descent.png)
 
 双下降现象中描绘模型泛化性能的曲线图由三个阶段组成：
 1. 第一阶段：当模型规模小且数据量不足时，模型泛化性能较差。

diff --git a/docs/chapter3/chapter3.md → docs/chapter3.md b/docs/chapter3/chapter3.md → docs/chapter3.md
@@ -61,6 +61,6 @@ $$
 
 **示例：**对于二维空间$R^2$中的三个点，线性分类器$sign(wx+b)$可以实现三点的所有对分，但无法实现四点的所有对分，如下图所示：
 
-![shattering](../images/shattering.png)
+![shattering](images/shattering.png)
 
 因此，线性分类器在$R^2$中的VC维为3。
diff --git a/docs/chapter4/chapter4.md → docs/chapter4.md b/docs/chapter4/chapter4.md → docs/chapter4.md
diff --git a/docs/chapter5/chapter5.md → docs/chapter5.md b/docs/chapter5/chapter5.md → docs/chapter5.md
diff --git a/docs/chapter6/chapter6.md → docs/chapter6.md b/docs/chapter6/chapter6.md → docs/chapter6.md
@@ -56,7 +56,7 @@ $$
 
 一个典型的例子是我们熟悉的决策树模型：
 
-![decision_tree](../images/decision_tree.png)
+![decision_tree](images/decision_tree.png)
 
 每当构造一个决策树的节点时，相当于在样本空间上进行了一次划分（即划分机制）。这种洞察方式同样适用于解释剪枝操作，即通过减少不必要的节点来简化树结构，同时保持或提高模型的性能。
 

diff --git a/docs/chapter7/chapter7.md → docs/chapter7.md b/docs/chapter7/chapter7.md → docs/chapter7.md
diff --git a/docs/chapter8/chapter8.md → docs/chapter8.md b/docs/chapter8/chapter8.md → docs/chapter8.md
diff --git a/docs/images/img.drawio → docs/images/images.drawio b/docs/images/img.drawio → docs/images/images.drawio
diff --git a/docs/images/mlt.jpg → docs/images/original_book.jpg b/docs/images/mlt.jpg → docs/images/original_book.jpg
diff --git a/docs/images/qr.jpeg → docs/images/qr_code.jpg b/docs/images/qr.jpeg → docs/images/qr_code.jpg
diff --git a/docs/references.md b/docs/references.md
@@ -0,0 +1,49 @@
+# 参考文献
+
+Abernethy, Jacob, et al. "Optimal strategies and minimax lower bounds for online convex games." Proceedings of the 21st annual conference on learning theory. 2008.
+
+Auer, Peter. "Using confidence bounds for exploitation-exploration trade-offs." Journal of Machine Learning Research 3.Nov (2002): 397-422.
+
+Bouneffouf, Djallel. "Finite-time analysis of the multi-armed bandit problem with known trend." 2016 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2016.
+
+Bubeck, Sébastien, Ronen Eldan, and Yin Tat Lee. "Kernel-based methods for bandit convex optimization." Journal of the ACM (JACM) 68.4 (2021): 1-35.
+
+Boyd, Stephen, and Lieven Vandenberghe. Convex optimization. Cambridge university press, 2004.
+
+Cesa-Bianchi, N., Conconi, A., and Gentile, C. "On the Generalization Ability of On-Line Learning Algorithms." IEEE Transactions on Information Theory, vol. 50, no. 9, 2004, pp. 2050-2057, doi:10.1109/TIT.2004.833339.
+
+Devroye, Luc, László Györfi, and Gábor Lugosi. A probabilistic theory of pattern recognition. Vol. 31. Springer Science & Business Media, 2013.
+
+Feller, William. "An introduction to probability theory and its applications." (1971).
+
+Flaxman, Abraham D., Adam Tauman Kalai, and H. Brendan McMahan. "Online convex optimization in the bandit setting: gradient descent without a gradient." arXiv preprint cs/0408007 (2004).
+
+Hazan, Elad, Amit Agarwal, and Satyen Kale. "Logarithmic regret algorithms for online convex optimization." Machine Learning 69.2 (2007): 169-192.
+
+Kakade, Sham M., and Ambuj Tewari. "On the generalization ability of online strongly convex programming algorithms." Advances in neural information processing systems 21 (2008).
+
+Kearns, Michael J., and Umesh Vazirani. An introduction to computational learning theory. MIT press, 1994.
+
+Lai, Tze Leung, and Herbert Robbins. "Asymptotically efficient adaptive allocation rules." Advances in applied mathematics 6.1 (1985): 4-22.
+
+McAllester, David A. "PAC-Bayesian stochastic model selection." Machine Learning 51.1 (2003): 5-21.
+
+Mohri, Mehryar. "Foundations of machine learning." (2018).
+
+Nakkiran, Preetum, et al. "Deep double descent: Where bigger models and more data hurt." Journal of Statistical Mechanics: Theory and Experiment 2021.12 (2021): 124003.
+
+Penot, Jean-Paul. "On regularity conditions in mathematical programming." Optimality and Stability in Mathematical Programming (1982): 167-199.
+
+Robbins, Herbert. "Some aspects of the sequential design of experiments." (1952): 527-535.
+
+Thompson, William R. "On the likelihood that one unknown probability exceeds another in view of the evidence of two samples." Biometrika 25.3-4 (1933): 285-294.
+
+Wainwright, Martin J. High-dimensional statistics: A non-asymptotic viewpoint. Vol. 48. Cambridge university press, 2019.
+
+Wang, Guanghui, Shiyin Lu, and Lijun Zhang. "Adaptivity and optimality: A universal algorithm for online convex optimization." Uncertainty in Artificial Intelligence. PMLR, 2020.
+
+Zhang, Lijun, Shiyin Lu, and Zhi-Hua Zhou. "Adaptive online learning in dynamic environments." Advances in neural information processing systems 31 (2018)
+
+Zhang, Lijun, Tie-Yan Liu, and Zhi-Hua Zhou. "Adaptive regret of convex and smooth functions." International Conference on Machine Learning. PMLR, 2019.
+
+Zinkevich, Martin. "Online convex programming and generalized infinitesimal gradient ascent." Proceedings of the 20th international conference on machine learning (icml-03). 2003.