Subexponential-Time Algorithms for Sparse PCA

07/26/2019
by   Yunzi Ding, et al.
0

We study the computational cost of recovering a unit-norm sparse principal component x ∈R^n planted in a random matrix, in either the Wigner or Wishart spiked model (observing either W + λ xx^ with W drawn from the Gaussian orthogonal ensemble, or N independent samples from N(0, I_n + β xx^), respectively). Prior work has shown that when the signal-to-noise ratio (λ or β√(N/n), respectively) is a small constant and the fraction of nonzero entries in the planted vector is x_0 / n = ρ, it is possible to recover x in polynomial time if ρ≲ 1/√(n). While it is possible to recover x in exponential time under the weaker condition ρ≪ 1, it is believed that polynomial-time recovery is impossible unless ρ≲ 1/√(n). We investigate the precise amount of time required for recovery in the "possible but hard" regime 1/√(n)≪ρ≪ 1 by exploring the power of subexponential-time algorithms, i.e., algorithms running in time (n^δ) for some constant δ∈ (0,1). For any 1/√(n)≪ρ≪ 1, we give a recovery algorithm with runtime roughly (ρ^2 n), demonstrating a smooth tradeoff between sparsity and runtime. Our family of algorithms interpolates smoothly between two existing algorithms: the polynomial-time diagonal thresholding algorithm and the (ρ n)-time exhaustive search algorithm. Furthermore, by analyzing the low-degree likelihood ratio, we give rigorous evidence suggesting that the tradeoff achieved by our algorithms is optimal.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset