3 problems

0 votes0 replies1 view
The minimax regret conjecture for stochastic bandit convex optimization
Let $d$ be the dimension, let $\calA$ denote the action space, and let $\mathfrak R_T^\star(d;\calA)$ be the minimax expected regret after $T$ rounds in stochastic bandit convex op…
Conjectureopenbandit-convex-optimization minimax-lower-bounds online-learningarXiv posted 2 days ago
0 votes0 replies1 view
Conjectured complexity bound for a one-point feedback algorithm
Bubeck–Kleinberg–Slivkins conjecture. Their algorithm has complexity
Conjectureopenbandit-convex-optimization derivative-free-optimization stochastic-optimizationarXiv posted 2 days ago
0 votes0 replies0 views
Conjecture on optimal regret for adversarial bandit convex optimization
Optimal bandit convex optimization regret conjecture. There exists an algorithm whose steps take …
Conjectureopenbandit-convex-optimization online-learning regret-boundsarXiv posted 2 days ago

The minimax regret conjecture for stochastic bandit convex optimization