Unverified50% confidenceFactExact time
All previous algorithms for this problem require superpolynomial time in k or 1/ε, or rely on strong well-conditioned assumptions.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPreviously, the best known algorithms for the fixed-point problem of ℓ∞ contraction maps were exponential-time algorithms based on the simplex method, or polynomial-time algorithms for special structures.75% similarUnverifiedThis work proposes the first algorithm that learns k arbitrary positive linear combinations of ReLUs in fully polynomial time without strong assumptions (with respect to the Gaussian distribution and L2 loss, both sample and time complexity are poly(d, k, 1/ε)).71% similarUnverifiedSemidefinite programming is a convex optimization problem that constrains decision variables to be positive semidefinite matrices; it is a convex problem solvable in polynomial time and yields a globally optimal solution.67% similarUnverifiedNP-completeness theory is built on reduction: if problem A can be transformed into problem B in polynomial time, then an algorithm that solves B also solves A.67% similarUnverifiedThe introduction of the monotone operator endows what might otherwise be a non-convex optimization problem with favorable mathematical structure, thereby ensuring the algorithm's computational efficiency.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098111API
curl https://kongchang.com/api/v1/knowledge/claims/1098111MCP
get_claim(id=1098111)