Unverified50% confidenceFactExact time
For ordinary unweighted observations, when the loss is a degree-D polynomial, exactly r=C(d+D, D)-1 coordinates are required.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFor non-quadratic distribution families with bounded third-order skewness and finite Fisher–Rao diameter, R is bounded by a constant independent of dimension d.72% similarUnverifiedIn ridge regression, storing only the predictor costs dp, whereas an exact learning state requires dp + d(d+1)/2, with the additional d(d+1)/2 corresponding to the second-order covariance structure information of the design matrix.69% similarUnverifiedFor smooth convex residual losses, under the premise that both features and labels are unconstrained real numbers, a fixed-dimensional exact continuous recurrent state exists if and only if the loss function is a polynomial.67% similarUnverifiedNon-polynomial losses have unbounded state requirements over histories with equal predictions, and this obstacle persists for bounded scalar logistic loss even after fixing an arbitrary finite-order jet of derivatives.66% similarUnverifiedIn robust regression, replacing the likelihood function from Gaussian to a t-distribution is equivalent to reducing the weight of outliers in the loss function.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002200API
curl https://kongchang.com/api/v1/knowledge/claims/1002200MCP
get_claim(id=1002200)