Unverified50% confidenceOpinionExact time
The linear assumption may fail to capture complex nonlinear decision boundaries.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe linear assumption that more parameters means greater capability does not necessarily hold, and blindly stacking parameters may not improve performance.77% similarUnverifiedThe fact that adding a quadratic or nonparametric term is not significant does not mean nonlinearity is absent; error may be masking it.74% similarUnverifiedTo truly achieve reasoning rather than merely attaining in-distribution accuracy, it is not sufficient to simply have the hypothesis class cover the correct rules.74% similarUnverifiedTopology-based measures of expressive power that rely on decision boundaries are not applicable to regression problems or other tasks that do not involve decision boundaries.72% similarUnverifiedForward decoding accuracy alone cannot prove that the probed factor is aligned with the dominant geometry of the representation, and the success of a linear probe should not be simply equated with the model having learned a linear and low-dimensional representation.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115391API
curl https://kongchang.com/api/v1/knowledge/claims/1115391MCP
get_claim(id=1115391)