Machine learning for statistics
Graduate · Statistics
Syllabus focus
Standard syllabus · STEM / applied
Pricing
Graduate-level rates are set on consultation. See the pricing page for K–12 and undergraduate rates.
Topics typically covered
Standard syllabus
Statistical learning foundations
- Loss functions and empirical risk minimization
- Bias-variance and generalization error
- VC dimension and complexity control (intro)
- Regularization paths and model selection
- Cross-validation theory and practice
Modern methods
- Ensemble learning: boosting and bagging
- Kernel methods and SVMs
- Neural networks from a statistical view
- Unsupervised learning: clustering and embeddings
- Feature selection and sparsity
Evaluation and deployment
- Proper scoring rules
- Calibration and fairness metrics
- Interpretability: SHAP and LIME (overview)
- Statistical inference after model selection (intro)
STEM / applied
Applied ML for statisticians
- PyTorch or TensorFlow for statisticians (intro)
- GPU training and batching basics
- MLOps and reproducible experiment tracking
- Case studies in vision, NLP, and tabular data
- Transfer learning and fine-tuning (overview)
- Deploying models with monitoring and drift detection
Additional applied practice
- Reviewing assumptions with domain experts
- Documenting analysis choices for reproducibility
- Sensitivity analyses for key modeling decisions
- Connecting results to the original research or business question
Notes
Graduate course bridging statistical learning and modern ML. Applied sections emphasize implementation; standard sections cover theory and generalization.