這兩天閑來沒事，就總結了一下機器學習中與機率相關的内容= =
推薦一些相關文獻：
1.生成模型：
(1)VAE：An Introduction to Variational Autoencoders、變分推斷與變分自編碼器(VAE)
(2)GAN：A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
(3)Flow：Normalizing Flows: An Introduction and Review of Current Methods
(4)Autoregressive Models: introduction for Autoregressive Models
2.divergence：
(1)f-divergence: f-Divergences and Surrogate Loss Functions
(2)Wasserstein distance:【數學】Wasserstein Distance
(3)Stein discrepancy: Stein’s Method for Practical Machine Learning
(4)Fisher divergence: Variational approximations using Fisher divergence
(5)Sliced method for computation acceleration:
a.Fisher divergence: Sliced Score Matching: A Scalable Approach to Density and Score Estimation
b.Wasserstein distance: Generalized Sliced Wasserstein Distances
3.BNN和dropout
(1)BNN:Bayesian Neural Networks
(2)dropout:深度學習中Dropout原了解析
4.貝葉斯元學習：
(1)神經過程：Neural Processes
(2)貝葉斯+MAML：Amortized Bayesian Meta-Learning、Bayesian Model-Agnostic Meta-Learning、Probabilistic Model-Agnostic Meta-Learning
5.高斯過程：Gaussian Processes in Machine Learning
6.表示學習：
(1)資訊瓶頸：資訊瓶頸理論-基礎與應用
(2)解耦表示學習：【Disentangled representation 1】InfoGAN與betaVAE
(3)infoMAX和contrastive learning:Deep InfoMax: Learning good representations through mutual information maximization、A Simple Framework for Contrastive Learning of Visual Representations
7.其他：
(1)資訊論：INTRODUCTION TO INFORMATION THEORY
(2)測度論：sola的數學筆記
(3)MCMC：馬爾可夫鍊蒙特卡羅算法（MCMC）
(4)gradient flow：Gradient Flow
(5)貝葉斯優化：貝葉斯優化(Bayesian Optimization)深入了解
(6)其他論文：
Meta Dropout: Learning to Perturb Features for Generalization
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
Functional Variational Bayesian Neural Networks
Variational Implicit Processes
The Functional Neural Process
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning