CRW-FTRL matches corruption-free regret under strong bandit corruption
For K actions in d dimensions it reaches Õ(√(dT log K)+dC) regret and settles the compact-set rate.
Stories per day · 30 days
1 stories, newest first · one card per story
1 stories, newest first · one card per story
For K actions in d dimensions it reaches Õ(√(dT log K)+dC) regret and settles the compact-set rate.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views