Unverified50% confidenceFactExact time
The current best regret upper bound scales as √(Tγ_T) up to logarithmic factors.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
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.69% 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).68% similarVerifiedNumerical gradient checking approximates gradients using the central difference formula (f(θ+ε) - f(θ-ε)) / (2ε) and compares them with analytical gradients; a relative error below 1e-5 is considered correct, while an error above 1e-3 almost certainly indicates a bug.60% similarUnverifiedThe new sample complexity bound matches the known lower bound in its exponential dependence on |β|/(1-γ).56% similarUnverifiedULP (Unit in the Last Place) refers to the smallest interval representable by a floating-point number at its current value, and its magnitude depends on the scale of the value itself.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990862API
curl https://kongchang.com/api/v1/knowledge/claims/990862MCP
get_claim(id=990862)