SHapley Additive exPlanations (SHAP)
A Unified Approach to Interpreting Model Predictions
Introduction
Explanation model
Viewing any explanation of a model’s prediction as a model itself.
Application of game theory
Game theory results guaranteeing a unique solution apply to the entire class of additive feature attribution methods and propose SHAP values as a unified measure ...
XGBoost
XGBoost: A Scalable Tree Boosting System
Introduction
Designs introduced scalability to XGBoost
A novel tree learning algorithm is for handling sparse data.
A theoretically justified weighted quantile sketch procedure enables handling instance weights in approximate tree learning.
Tree Boosting In a Nutshell
R...
Section 1.3
Chapter 1 Statistical Models, Goals, And Performance Criteria
1.3 The Decision Theoretic Framework
Decision Theoretic Framework
Basic elements of a decesion problem
Estimation
Estimating a real parameter $\theta\in\Theta$ using data $X$ with conditional distribution $P_\theta$.
Testing
Given data $X\sim P_\theta$, ...
Section 1.2
Chapter 1 Statistical Models, Goals, And Performance Criteria
1.2 Bayesian Models
Bayesian Framework
Statistical Model
A random variable $X$
$\mathcal{X}$: Sample Space = {outcomes x}
$\mathcal{F}_X$: sigma-field of measurable events
$P(\cdot)$: probability distribution defined on $(\mathca...
Regularization
Regularization
Overview
Definition
In general: Any method to prevent overfitting or help the optimization.
Specifically: Additional terms in the training optimization objective to prevent overfitting or help the optimization.
Overfitting
Key: empirical loss and expected loss are different.
Smaller the data set, larger the difference...
Back Propagation
Back Propagation
Perceptrons
A toy model of perceptrons
The perceptron training rule
Initialize weights $w=0$
Iterate through training instances until convergence
Calculate the output for the given instances.
\(o = \begin{cases}
1 \,\, if\,\,w_0 + \sum_{i=1}^n w_ix_i>0 \\
0 \,\,o.w.
\end{cases}\)
Update each w...
Naive Bayes and Probability Graphical Model Intro
Naive Bayes
Basic Ideas
Supervised Learning
Problem Setting:
Set of possible instances: $X$
Unknown target function (concept): $f: X\rightarrow Y$
Set of hypotheses (hypothesis class): $H = {h\lvert h:X\rightarrow Y}$
Given:
Training set of instances of unknown target function $f$, $(x^{(1)}, y^{(1)})$, $(x^{(2)}, y^{(2)})$, … , $(x...
Section 1.1
Chapter 1 Statistical Models, Goals, And Performance Criteria
1.1 Data, Models, Parameters and Statistics
Definition of Statistical Model
Random experiment with sample space $\Omega$.
Random vector $X=(X_1, \ldots, X_n)$ defined on $\Omega$.
$\omega \in \Omega$: outcome of experiment
$X(\omega)$: data observations
...
13 post articles, 2 pages.