# Statistics and ML

## Paradigms and problems

## Methods for structured data

- Statistical relational learning, or machine learning on relational data
- Symbolic regression
- Word embeddings and graph embeddings
- Graph kernels, including both kernels
*on*graphs and kernels*between*graphs

## Basic concepts and tools

- Markov chains and kernels
- Statistical distances, i.e., distances between probability distributions
- Copulas and measures of dependence
- Error estimation
- Symmetry in probability and statistics
- Stability and its connection to generalization
- Differential privacy