Unverified50% confidenceFactExact time
For weakly observable graph bandits, the known minimax regret lower bound is Θ(T^{2/3}), where T is the total number of rounds.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe paper proves that for the Matérn-ν kernel with parameter ν∈(0,2), the γ-exponential kernel with parameter γ∈(0,2), and certain piecewise polynomial kernels, the minimax optimal rate is precisely determined to be Θ(√(Tγ_T)), with upper and lower bounds matching within constant factors.72% similarUnverifiedThe paper derives the closed-form solution for the optimal guidance weight that minimizes mean squared error: λ*(T, δ, σ₀²) = σ₀² / (σ₀² + R_max² · δ² · T).69% similarUnverifiedUnder mild conditions satisfied by common kernel functions, minimizing the kernel-specific upper bound yields a number of replications of Θ(log T).68% similarUnverifiedThe current best regret upper bound scales as √(Tγ_T) up to logarithmic factors.68% similarUnverifiedThe Lovász condition is ‖b*ₖ‖² ≥ (δ - μ²ₖ,ₖ₋₁)·‖b*ₖ₋₁‖², where δ is typically set to 3/4.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133667API
curl https://kongchang.com/api/v1/knowledge/claims/1133667MCP
get_claim(id=1133667)