note
2022/11/17 18:19:00
note
causal discovery
paper list
survey
structural causal model
toolbox
- 调研近年因果发现的最新研究
- 将”因果发现”与”根因分析”以及”基于因果图的因果发现”等概念理清关系
- 从优化的角度重新看待三类因果发现算法, 这可以帮助我们借鉴已有方法到自己的工作中。
- 总结用于因果发现的各种包, 以及Github上star较多的Repositories
2021/03/30 18:00:00
note
- posterior collapse: where the latents are ignored when they are paired with a powerful autoregressive decoder — typically observed in the VAE framework, i.e., the latents are ignored as the decoder is powerful enough to model x perfectly.个人理解是某些VAE的decoder的重建能力过于好导致重建误差很小,最后模型不能很好的最小化prior相关的loss item。
Self-supervised learning survey
2020/07/30 15:00:00
note
self-supervised learning