Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



REPORTS > DETAIL:

Paper:

TR17-115 | 5th July 2017 11:27

Hardness of learning noisy halfspaces using polynomial thresholds

RSS-Feed




TR17-115
Authors: Arnab Bhattacharyya, Suprovat Ghoshal, Rishi Saket
Publication: 5th July 2017 11:47
Downloads: 963
Keywords: 


Abstract:

We prove the hardness of weakly learning halfspaces in the presence of adversarial noise using polynomial threshold functions (PTFs). In particular, we prove that for any constants $d \in \mathbb{Z}^+$ and $\epsilon > 0$, it is NP-hard to decide: given a set of $\{-1,1\}$-labeled points in $\mathbb{R}^n$ whether (YES Case) there exists a halfspace that classifies $(1-\epsilon)$-fraction of the points correctly, or (NO Case) any degree-$d$ PTF classifies at most $(1/2 + \epsilon)$-fraction of the points correctly. This strengthens to all constant degrees the previous NP-hardness of learning using degree-$2$ PTFs shown by Diakonikolas et al. (2011). The latter result had remained the only progress over the works of Feldman et al. (2006) and Guruswami et al. (2006) ruling out weakly proper learning adversarially noisy halfspaces.



ISSN 1433-8092 | Imprint