classifier-free guidance does: interpolates between conditional and unconditional generation

Boosting (machine learning)

Boosting reduces bias in ML models

soft targets carry more information than hard labels: they encode class similarities

Why do some learning methods need to explore more than others?

score matching does: learns the gradient of the log-density without normalizing

Ever wonder how we can compare apples and oranges fairly in studies?

the condition number κ(A) measures: sensitivity of Ax=b to perturbations

How small changes affect big outcomes

Adam vs SGD: Adam adapts per-parameter rates, SGD often generalizes better with tuning

Adam adjusts learning rates per-parameter, SGD generalizes better with tuning

to standardize: when you need zero mean and unit variance for gradient-based optimization

Why do we need to make data uniform before training a model?