Mathematics – Statistics Theory
Scientific paper
2009-05-05
Mathematics
Statistics Theory
Presented in part at NIPS 2008 conference, Vancouver, Canada, December 2008
Scientific paper
Consider the use of $\ell_{1}/\ell_{\infty}$-regularized regression for joint estimation of a $\pdim \times \numreg$ matrix of regression coefficients. We analyze the high-dimensional scaling of $\ell_1/\ell_\infty$-regularized quadratic programming, considering both consistency in $\ell_\infty$-norm, and variable selection. We begin by establishing bounds on the $\ell_\infty$-error as well sufficient conditions for exact variable selection for fixed and random designs. Our second set of results applies to $\numreg = 2$ linear regression problems with standard Gaussian designs whose supports overlap in a fraction $\alpha \in [0,1]$ of their entries: for this problem class, we prove that the $\ell_{1}/\ell_{\infty}$-regularized method undergoes a phase transition--that is, a sharp change from failure to success--characterized by the rescaled sample size $\theta_{1,\infty}(n, p, s, \alpha) = n/\{(4 - 3 \alpha) s \log(p-(2- \alpha) s)\}$. An implication of this threshold is that use of $\ell_1 / \ell_{\infty}$-regularization yields improved statistical efficiency if the overlap parameter is large enough ($\alpha > 2/3$), but has \emph{worse} statistical efficiency than a naive Lasso-based approach for moderate to small overlap ($\alpha < 2/3$). These results indicate that some caution needs to be exercised in the application of $\ell_1/\ell_\infty$ block regularization: if the data does not match its structure closely enough, it can impair statistical performance relative to computationally less expensive schemes.
Negahban Sahand
Wainwright Martin J.
No associations
LandOfFree
Simultaneous support recovery in high dimensions: Benefits and perils of block $\ell_1/\ell_\infty$-regularization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Simultaneous support recovery in high dimensions: Benefits and perils of block $\ell_1/\ell_\infty$-regularization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Simultaneous support recovery in high dimensions: Benefits and perils of block $\ell_1/\ell_\infty$-regularization will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-450952