Unverified50% confidenceFactExact time
Regardless of which regime applies, estimators based on compression complexity stably maintain a convergence rate of O(1/√N).
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe importance sampling optimization idea can compress the actual algorithmic complexity from O(N) to O(k), where k is much smaller than N.73% similarUnverified缩放点积将点积除以√d（d为嵌入维度），使点积方差保持在合理范围，让Softmax输出更平滑的概率分布以稳定训练71% similarUnverifiedThe computational complexity of the prefill stage has a quadratic relationship with sequence length (O(n²)).71% similarUnverifiedThe O(1/√N) convergence rate cannot be further improved in the sense of rates, representing that risk estimation has reached the information-theoretically optimal rate.71% similarUnverifiedA domain decomposition strategy can reduce the step complexity from O((L/w)²) to O(L²/(N·w²)), where N is the number of subdomains.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001356API
curl https://kongchang.com/api/v1/knowledge/claims/1001356MCP
get_claim(id=1001356)