📚 Josh's Notes

Machine Learning

Tag Index

Home

👋 Hi there! My name is Josh Fleming.

Logistic Regression and Laplace's Approximation

Logistic Regression When we train a logistic regression model, we find the maximum of the following likelihood function across the training data set (disregard regularization for now): \mathcal{L}(x;\beta) = \prod_{i=1}^n g(x_i^\top \beta)^{y_i} \cdot (1 - g(x_i^\top \beta))^{1 - y_i} Here, x_i repr...

Learning to Rank with Linear Models

Most active research and applications of learning to rank algorithms focus on nonlinear modeling techniques like SVMs and boosted decision trees.