Machine learning
Graduate · CS / Programming
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
Learning theory
- PAC learning framework and VC dimension (intro)
- Bias–variance and regularization paths
- Convex losses and risk minimization
- Generalization bounds overview (intro)
- Model selection and information criteria
Optimization for ML
- Gradient descent, SGD, and momentum methods
- Convex optimization review for ML
- Lagrange multipliers and duality in SVMs
- Proximal methods and sparsity (intro)
- Second-order methods (Newton, L-BFGS intro)
STEM / applied
Advanced models
- Kernel methods and Gaussian processes (intro)
- Deep learning architectures: CNNs, RNNs, Transformers (survey)
- Generative models: VAEs, GANs, diffusion (survey)
- Reinforcement learning basics: MDPs, Q-learning (intro)
- Causal inference connections to ML (intro)
Research skills
- Reproducing papers and ablation studies
- Experiment tracking and hyperparameter sweeps
- Responsible ML: fairness, privacy, robustness
- Scaling training: distributed data parallel (intro)
- Reading and presenting NeurIPS/ICML papers
Notes
Mathematical maturity in probability, linear algebra, and optimization expected.