4 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 replies0 views
The wider-regime conjecture for minimax lower bounds in off-policy evaluation
Wider-regime conjecture. A similar lower bound should hold in the wider regime $\nu_0^{-1}\lesssim n\lesssim|\mathcal{S}|$ .
Conjectureopenminimax-lower-bounds off-policy-evaluation reinforcement-learningarXiv posted 2 days ago
0 votes0 replies0 views
Generalization of the single-trajectory lower-bound construction for ordinary differential equations
Single-trajectory generalization conjecture. Similar arguments should establish the same lower bounds for arbitrary $d\in\mathbb{N}_{\geq 2}$ and $\beta\in\mathbb{R}_{\geq 1}$ , wit…
Conjectureopenminimax-lower-bounds nonparametric-estimation ordinary-differential-equationsarXiv posted 2 days ago
0 votes0 replies0 views
The factor- $H$ minimax lower-bound conjecture for non-stationary finite-horizon MDPs
The factor- $H$ minimax lower-bound conjecture. The minimax lower bound for the non-stationary finite-horizon MDP setting should be a factor of $H$ larger than the corresponding low…
Conjectureopenminimax-lower-bounds reinforcement-learning sample-complexityarXiv posted 2 days ago

4 problems

The minimax regret conjecture for stochastic bandit convex optimization

The wider-regime conjecture for minimax lower bounds in off-policy evaluation

Generalization of the single-trajectory lower-bound construction for ordinary differential equations

The factor-HHH minimax lower-bound conjecture for non-stationary finite-horizon MDPs

The factor- $H$ minimax lower-bound conjecture for non-stationary finite-horizon MDPs