Advanced ML
Learning theory, gradient boosting internals, uncertainty, self-supervised learning, generative models, and causal inference. Assumes Foundations and Deep Learning.
0 / 31 solved
-
Learning Theory & Phenomena
Double descent, shift estimation, and the infinite-width NTK regime.
-
Gradient Boosting Internals
Elastic Net, and the tricks inside XGBoost and LightGBM.
-
Uncertainty & Bayesian
Conformal prediction, deep ensembles, and posterior predictive distributions.
-
Self-Supervised & Representation Learning
Contrastive learning (SimCLR, InfoNCE) and non-contrastive methods (VICReg).
-
Causal Inference
Overlap, cross-fitting, double robustness, Neyman orthogonality, and doubly-robust policy evaluation.
-
Generative Models
VAEs and posterior collapse, diffusion (DDPM), normalizing flows, and GAN basics.