armin

Hi. here are published ARC-2 weight estimated generalization bounds using paper data: [hoeffding] n=1000, correct=403, delta=0.05 | emp_acc=40.30% -> acc_lower=36.01% (err_upper=63.99%) [empirical_bernstein] n=1000, correct=403, delta=0.05 | emp_acc=40.30% -> acc_lower=34.63% (err_upper=65.37%)...

HRM implication for hierarchical data understanding

1

What is HRM performance on hierarchical data and tree structures encoding? Thanks.