Unverified50% confidenceFactExact time
Greedy approximation of submodular functions has a theoretical optimality guarantee of (1−1/e) ≈ 63%.
1
Sources
50%
Confidence
Long-term
Relevance
10/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBayesian decision theory selects the action a* that minimizes expected loss, i.e., a* = argmin_a E[L(θ, a)|x], where the expectation is taken with respect to the posterior distribution p(θ|x).63% similarUnverifiedThe performance of current state-of-the-art models on the highest difficulty tier of FrontierMath is typically only in the single-digit to double-digit percentage range.62% similarUnverifiedThe Sharpe ratio was proposed by Nobel Economics Prize laureate William Sharpe and is calculated as the strategy's excess return divided by the standard deviation of returns.59% similarUnverifiedUnder the assumption that the true mapping is uniformly random, the paper proves a lower bound on the error rate of E ≥ (M/N)δ*(B/M) + (1-M/N)(1-1/K).59% similarUnverifiedThe advantage function A(s,a) = Q(s,a) - V(s); in practical PPO implementations, Generalized Advantage Estimation (GAE) is typically used, with typical settings of λ = 0.95 and γ = 0.99.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/964123API
curl https://kongchang.com/api/v1/knowledge/claims/964123MCP
get_claim(id=964123)