Search Results for author:
Found 2 papers, 0 papers with code
An exactly solvable model for emergence and scaling laws
Deep learning models can exhibit what appears to be a sudden ability to solve a new problem as training time ($T$), training data ($D$), or model size ($N$) increases, a phenomenon known as emergence.
Why flatness does and does not correlate with generalization for deep neural networks
As an alternative to flatness measures, we use a function based picture and propose using the log of Bayesian prior upon initialization, $\log P(f)$, as a predictor of the generalization when a DNN converges on function $f$ after training to zero error.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
