Explores diffusion models, focusing on generating samples from a distribution and the importance of denoising in the process.
Explores the Exponential Family distribution, covering entropy, energy, and moments.
Explores learning the kernel function in convex optimization, focusing on predicting outputs using a linear classifier and selecting optimal kernel functions through cross-validation.
Introduces the Random-Subcube Model (RSM) for constraint satisfaction problems, exploring its structure, phase transitions, and variable freezing.
Covers the KKT conditions and convex optimization, discussing constraint qualifications and tangent cones of convex sets.
