Unverified50% confidenceFactExact time
In the stochastic environment, the regret of the paper's algorithm is \tilde{\mathcal{O}}(δ_* \log T / Δ_{\min}^2), where Δ_{\min} is the minimum suboptimality gap.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the adversarial environment, the regret of the paper's algorithm is \tilde{\mathcal{O}}(δ_*^{1/3} T^{2/3}), where δ_* is the fractional weak domination number.78% similarUnverifiedUnder the premises of smooth stochastic nonconvexity, a global lower bound for the population objective, and a second-moment bound on the sample Lipschitz constant, the paper gives a scalar oracle lower bound of Ω(d L_0^2 min{ΔH, L_0^2} / ε^4), which is linear in d and ε^{-4} in accuracy.67% similarUnverifiedIn finite-action-set linear bandit problems, the adversarial environment requires the algorithm to guarantee ~O(√T) regret, and the stochastic environment expects O(log T)-level regret.65% similarUnverifiedThe Gaussian distribution PDF contains the term exp(-x²/2σ²), which underflows to zero when x is far from the mean or σ is extremely small; therefore, in practice the log-PDF is commonly computed in log space to ensure numerical stability.65% similarUnverifiedThe Min-Max normalization formula is (x - min) / (max - min), which linearly maps data to [0,1] but is extremely sensitive to outliers.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1133672API
curl https://kongchang.com/api/v1/knowledge/claims/1133672MCP
get_claim(id=1133672)