Reproducing Deep Double Descent
June 13, 2020 | 7 min readDouble descent is one of the mysteries of modern machine learning. I reproduced the main results of the recent paper by Nakkiran et al. and posed some questions that occurred to me.
![[object Object]](/static/2d0f4e01d6e61412b3e92139e5695299/d8057/profile-pic.webp)
Hippocampus's Garden
Under the sea, in the hippocampus's garden...
Tags
- algorithm (1)
- aoty (3)
- book (15)
- career (3)
- causal-inference (2)
- cloud (1)
- cv (8)
- data-analysis (7)
- deep-learning (20)
- en (60)
- food (3)
- france (3)
- gadget (1)
- gatsby (4)
- golang (2)
- graph (2)
- ja (32)
- kaggle (7)
- machine-learning (10)
- math (10)
- matplotlib (1)
- misc (7)
- music (7)
- nlp (9)
- pandas (5)
- playlist (4)
- programming (8)
- python (24)
- react (1)
- react-native (1)
- reinforcement-learning (1)
- stats (8)
- transformer (1)
- web (1)