Beyond Sub-Gaussian Measurements: High-Dimensional Structured Estimation with Sub-Exponential Designs

نویسندگان

  • Vidyashankar Sivakumar
  • Arindam Banerjee
  • Pradeep Ravikumar
چکیده

We consider the problem of high-dimensional structured estimation with norm-regularized estimators, such as Lasso, when the design matrix and noise are drawn from sub-exponential distributions. Existing results only consider sub-Gaussian designs and noise, and both the sample complexity and non-asymptotic estimation error have been shown to depend on the Gaussian width of suitable sets. In contrast, for the sub-exponential setting, we show that the sample complexity and the estimation error will depend on the exponential width of the corresponding sets, and the analysis holds for any norm. Further, using generic chaining, we show that the exponential width for any set will be at most [Formula: see text] times the Gaussian width of the set, yielding Gaussian width based results even for the sub-exponential case. Further, for certain popular estimators, viz Lasso and Group Lasso, using a VC-dimension based analysis, we show that the sample complexity will in fact be the same order as Gaussian designs. Our general analysis and results are the first in the sub-exponential setting, and are readily applicable to special sub-exponential families such as log-concave and extreme-value distributions.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Sigma-Delta quantization of sub-Gaussian frame expansions and its application to compressed sensing

Suppose that the collection {ei}i=1 forms a frame for R, where each entry of the vector ei is a sub-Gaussian random variable. We consider expansions in such a frame, which are then quantized using a Sigma-Delta scheme. We show that an arbitrary signal in R can be recovered from its quantized frame coefficients up to an error which decays root-exponentially in the oversampling rate m/k. Here the...

متن کامل

Estimation with Norm Regularization

Analysis of non-asymptotic estimation error and structured statistical recovery based on norm regularized regression, such as Lasso, needs to consider four aspects: the norm, the loss function, the design matrix, and the noise model. This paper presents generalizations of such estimation error analysis on all four aspects compared to the existing literature. We characterize the restricted error...

متن کامل

Stable Recovery of Structured Signals From Corrupted Sub-Gaussian Measurements

This paper studies the problem of accurately recovering a structured signal from a small number of corrupted sub-Gaussian measurements. We consider three different procedures to reconstruct signal and corruption when different kinds of prior knowledge are available. In each case, we provide conditions (in terms of the number of measurements) for stable signal recovery from structured corruption...

متن کامل

2 3 Se p 20 15 GENERALIZED q - GAUSSIAN VON NEUMANN ALGEBRAS WITH COEFFICIENTS , II . ABSENCE OF CENTRAL SEQUENCES

We show that the generalized q-gaussian von Neumann algebras with coefficients Γq(B,S⊗H) with B a finite dimensional factor, dim(Dk(S)) sub-exponential and the dimension of H finite and larger than a constant depending on q, have no non-trivial central sequences.

متن کامل

Multi-Area State Estimation Based on PMU Measurements in Distribution Networks

State estimation in the energy management center of active distribution networks has attracted many attentions. Considering an increase in complexity and real-time management of active distribution networks and knowing the network information at each time instant are necessary. This article presents a two-step multi-area state estimation method in balanced active distribution networks. The prop...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Advances in neural information processing systems

دوره 28  شماره 

صفحات  -

تاریخ انتشار 2015