Feb 9, 2014 · This result is the first known gap between polynomial and optimal algorithms for sparse linear regression, and does not depend on conjectures in ...
Abstract. Under a standard assumption in complexity theory (NP ⊂ P/poly), we demonstrate a gap be- tween the minimax prediction risk for sparse linear ...
People also ask
How to find the upper and lower bounds of polynomials?
What is the upper bound and lower bound theorem?
This result is the first known gap between polynomial and optimal algorithms for sparse linear regression, and does not depend on conjectures in average-case ...
This work shows that when the design matrix is ill-conditioned, the minimax prediction loss achievable by polynomial-time algorithms can be substantially ...
May 21, 2014 · Under a standard assumption in complexity theory (NP ⊂ P/poly), we demonstrate a gap between the minimax prediction risk for sparse linear ...
Lower Bounds on the Performance of Polynomial-Time Algorithms for Sparse Linear Regression. Authors: Yuchen Zhang, Martin Wainwright, Michael Jordan.
Jul 15, 2014 · Under a standard assumption in complexity theory (NP not in P/poly), we demonstrate a gap between the minimax prediction risk for sparse ...
Lower bounds on the performance of polynomial-time algorithms for sparse linear regression. Y. Zhang, M. Wainwright, and M. Jordan.
n “slow” rate. In this paper, we show that the slow rate is intrinsic to a broad class of M-estimators. In particular, for estimators based on minimizing a ...
Lower bounds on the performance of polynomial-time algo- rithms for sparse linear regression. In Conference on Learning. Theory, pages 921–948, 2014. [70] ...