MetaLearning and Neural Processes
Conditional neural processes
Gaussian processes and Baysian Optimization（高斯过程与贝叶斯优化）
[深度学习] History of Bayesian Neural Networks（贝叶斯神经网络历史）
Automating Dataset Comparison and Manipulation with Optimal Transport
[信息瓶颈] The Information Bottleneck Theory of Deep Neural Networks
Computational Optimal Transport
The information in a DNN
kernel Kmeans （核K-均值聚类）
Data covariance, domain shift and visualization
An Introduction to PAC Bayes
Intro to Kernel Density Estimation (KDE)
这位先生差点摧毁了数学
Principles for Tackling Distribution Shift_Pessimism,Adaptation,and Anticipation
EM Algorithm for Latent Variable Models
[机器学习] Invariant Risk Minimization（不变风险最小化）
Fisher Information matrix
Quantization and pruning （模型量化与剪枝）
Deep Ensembles_ A Loss Landscape Perspective (Paper解读)
L1正则为什么会带来稀疏性和鲁棒性？
