New answers tagged

0 votes

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

Going off of @Alberto's answer: I agree that you would just get ginormous predictions, but I am not convinced no pattern would be learnt: in your example, we would learn to avoid predictions near zero:...
BigMistake's user avatar
1 vote

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

In HMM, a simple mechanism to reduce overfitting and therefore generating variety in the system output is tweaking the transition matrix A and/or the symbol emission probability B. Allowing for some ...
Jaume Oliver Lafont's user avatar
2 votes

Would maximizing (instead of minimizing) error of an LLM/HMM lead to complex behavior?

You cannot really invert the loss, because that's undefined most likely. Take linear regression with OLS, then we know that the loss function is quadratic wrt the parameters (assuming to have 1 ...
Alberto's user avatar
  • 1,358
0 votes

What role does data quality plays in the LLM scaling laws?

is the set of values estimated by the Chinchilla scaling laws optimal for these smaller models with optimized data too? This is an open research question, but some research such as Beyond neural ...
Stella Biderman's user avatar

Top 50 recent answers are included