How Log-Likelihood Helps Approximate the True Data Distribution?

Multi-Arm Bandits

强化学习中对测试结果的理解

Stochastic Differential Equation (SDE)

Score-Matching Langevin Dynamics (SMLD)

Denoising Diffusion Probabilistic Model (DDPM)

Actor-Critic Methods

Policy Gradient Methods

Variational Auto-Encoder (VAE)

Duality

关于半正定规划(SDP)的一道有趣题目

Convex functions

Convex sets

矩阵的逆