flâneur — a map of the web's best reading

Hypothesis: gradient descent prefers general circuits - LessWrong

lesswrong.com · 7,638 words · saved by 1 readers

Summary: I discuss a potential mechanistic explanation for why SGD might prefer general circuits for generating model outputs. I use this preference to explain how models can learn to generalize even…

x Hypothesis: gradient descent prefers general circuits — LessWrong Gradient Descent Optimization AI Frontpage 46 Hypothesis: gradient descent prefers general circuits by Quintin Pope 8th Feb 2022 AI Alignment Forum 14 min read 26 46 Ω 20 Summary: I discuss a potential mechanistic explanation for why SGD might prefer general circuits for generating model outputs. I use this preference to explain how models can learn to generalize even after overfitting to near zero training error (i.e., grokking). I also discuss other perspectives on grokking and deep learning generalization. Additionally, I d

Explore this link on the map →

related reading