Unverified50% confidenceFactExact time
The convex combination constraint (coefficients non-negative and summing to 1) prevents the mixing weights from becoming numerically unstable due to coefficient extrapolation and constrains the weight scale, thereby reducing the risk of activation explosion or gradient vanishing during recursive iterations.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe eigenvalues of orthogonal matrix initialization have a modulus of 1, which neither grows nor decays exponentially under repeated matrix multiplication, effectively mitigating vanishing and exploding gradients.70% similarUnverifiedWhen the spectral radius of the combined operator is less than 1, the iterative process converges stably to a fixed point.70% similarUnverifiedThe separation result generalizes to weighted fixed-count targets, as long as the weight ratios are bounded and the quota proportions are bounded away from 0 and 1, the separation holds even without permutation symmetry.70% similarUnverifiedGiven sufficient coverage and controlled local mechanism error, oracle-level causal composition can surpass the theoretical lower bound achievable by non-causal methods.69% similarUnverified哈达玛变换用于量化预处理时不会引入额外的数值不稳定性，因为其条件数恒为168% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1013270API
curl https://kongchang.com/api/v1/knowledge/claims/1013270MCP
get_claim(id=1013270)