Arnab Bhattacharyya: Hardness of Learning Noisy Halfspaces Using Polynomial Thresholds

Speaker: Arnab Bhattacharyya , IISc

Date: Thursday, May 11, 2017

Time: 2:00 PM to 3:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: 32-G575

Event Type:

Room Description:

Host: Pritish Kamath and Akshay Degwekar, CSAIL MIT

Contact: Rebecca Yadegar, ryadegar@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: seminars@csail.mit.edu, theory-seminars@csail.mit.edu

Reminder Subject: TALK: Arnab Bhattacharyya: Hardness of Learning Noisy Halfspaces Using Polynomial Thresholds

Abstract:
We prove the hardness of weakly learning halfspaces in the presence of adversarial noise using polynomial threshold functions (PTFs), assuming Khot's Unique Games Conjecture (UGC). In particular, we prove that for any constants d in? the positive integers? and eps > 0, assuming the UGC, it is NP-hard to decide: given a set of {-1,1}-labeled points in R^n whether (YES Case) there exists a halfspace that classifies (1-eps)-fraction of the points correctly, or (NO Case) any degree-d PTF classifies at most (1/2 + eps)-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.

Joint work with Suprovat Ghoshal (IISc) and Rishi Saket (IBM).

Research Areas:

Impact Areas:

See other events that are part of the Algorithms and Complexity Seminar Series 2016/2017.

Created by Rebecca Yadegar at Monday, May 08, 2017 at 1:18 PM.