Decision Tree
A classic supervised learning algorithm in machine learning that builds a tree-structured model for classification or regression by recursively partitioning datasets. Core mechanisms include purity metrics such as information gain and the Gini coefficient. Decision trees are known for their interpretability and ease of understanding.
Timeline (last 90 days)
Decision trees are widely used in scenarios that require explainable grounds, such as medical diagnosis and credit approval.
A decision model is essentially a reusable set of judgment logic, which can be as simple as a decision tree or a set of weighted scoring rules.
CLIC trains an interpretable decision tree to distinguish between the code collections of two LLMs.
The time complexity of brute-force searching for the optimal split point in a decision tree is O(n·m·log n), where n is the number of samples and m is the number of features, and this is the main bottleneck in decision tree training speed.
The construction of a decision tree is essentially a recursive process: at each node, data is split in two based on a certain feature and threshold, and this process is repeated on the subsets until a stopping condition is met.
Common techniques for limiting decision tree overfitting include restricting the maximum tree depth (max_depth), requiring nodes to contain at least N samples before splitting (min_samples_split), and post-pruning.
Bagging (Bootstrap Aggregating) trains multiple decision trees by sampling training data with replacement and aggregating predictions, effectively reducing variance and improving stability.
The biggest problem with a single decision tree is high variance and susceptibility to overfitting; ensemble learning compensates for this shortcoming through the trade-off of higher bias for lower variance.
决策树使用沿坐标轴的轴对齐分割，对特征的单调变换和局部拉伸不敏感，因此对保持类别排序的变换具有天然不变性
决策树及其集成版本（随机森林、XGBoost）对特征缩放不敏感，不需要像SVM或神经网络那样进行标准化预处理
3 more timeline events
All Facts (13)
Decision trees are widely used in scenarios that require explainable grounds, such as medical diagnosis and credit approval.
50%UnverifiedA decision model is essentially a reusable set of judgment logic, which can be as simple as a decision tree or a set of weighted scoring rules.
50%UnverifiedCLIC trains an interpretable decision tree to distinguish between the code collections of two LLMs.
50%UnverifiedThe time complexity of brute-force searching for the optimal split point in a decision tree is O(n·m·log n), where n is the number of samples and m is the number of features, and this is the main bottleneck in decision tree training speed.
50%UnverifiedThe construction of a decision tree is essentially a recursive process: at each node, data is split in two based on a certain feature and threshold, and this process is repeated on the subsets until a stopping condition is met.
50%UnverifiedCommon techniques for limiting decision tree overfitting include restricting the maximum tree depth (max_depth), requiring nodes to contain at least N samples before splitting (min_samples_split), and post-pruning.
50%UnverifiedBagging (Bootstrap Aggregating) trains multiple decision trees by sampling training data with replacement and aggregating predictions, effectively reducing variance and improving stability.
50%UnverifiedThe biggest problem with a single decision tree is high variance and susceptibility to overfitting; ensemble learning compensates for this shortcoming through the trade-off of higher bias for lower variance.
50%Unverified决策树使用沿坐标轴的轴对齐分割，对特征的单调变换和局部拉伸不敏感，因此对保持类别排序的变换具有天然不变性
50%Unverified决策树及其集成版本（随机森林、XGBoost）对特征缩放不敏感，不需要像SVM或神经网络那样进行标准化预处理
50%Unverified决策树的分裂准则（信息增益、基尼不纯度、均方误差）本质上是排序统计量的函数，只关心阈值两侧的类别比例而非样本间距离
50%Unverified决策树的分裂准则本质上是排序统计量的函数，对任何保持类别排序的单调变换具有不变性
50%Unverified该SWD特征变换实验在决策树上表现良好，但在逻辑回归、SVM、KNN等算法上效果糟糕
50%