Unverified50% confidenceFactExact time
The paper establishes a high-probability uniform mixing bound for the critically damped Metropolis-adjusted Langevin algorithm (with persistent uniform refresh), requiring O((κ^{1/2} + L_H^{1/2} m^{-3/4}) d^{1/4}) gradient evaluations (ignoring logarithmic factors), where κ = L/m is the condition number and d is the dimension.
1
Sources
50%
Confidence
Long-term
Relevance
11/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Stein identity states that for a function φ that decays sufficiently fast on the boundary, when the probability density p(x) is sufficiently smooth on R^d, E_p[∇_x log p(x)·φ(x) + ∇_x·φ(x)] = 0.75% 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.75% similarUnverifiedUnder the polynomial spectral decay (exponent α>1) and leverage compatibility assumptions, the squared L2 approximation rate of a two-layer network with width m and trainable proportion P is O((κ_P log(m/δ)/m)^α), where κ_P = (P/κ_1^* + (1-P)/κ_0^*)^{-1}.73% similarUnverifiedFor learning tasks operating on an intrinsic d*-dimensional submanifold, the paper proves that the optimal partition scaling can achieve the minimax nonparametric rate O(n^{-1/(d*+2)}√ln n).73% similarUnverifiedThe query complexity given in the paper for finding a Goldstein stationary point under first-order access (stochastic gradient queries) is O(δ⁻¹ε⁻³), where δ is the Goldstein radius and ε is the stationarity tolerance.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1179473API
curl https://kongchang.com/api/v1/knowledge/claims/1179473MCP
get_claim(id=1179473)