Robust Risk Minimization for Statistical Learning From Corrupted Data
نویسندگان
چکیده
منابع مشابه
Robust statistical learning from ‘ Big Network Data
The overarching theme of my research is on algorithms, analysis, and application of statistical signal processing tools to dynamic network health monitoring, social, power grid, and Big Network Data analytics. Experience, background, and current research include robust, distributed, and sparsity-aware learning from high-dimensional network data; which finds exciting applications in understandin...
متن کاملData recovery from corrupted observations via l1 minimization
This paper studies the problem of recovering a signal vector and the corrupted noise vector from a collection of corrupted linear measurements through the solution of a l1 minimization (2.1.2), where the sensing matrix is a partial Fourier matrix whose rows are selected randomly and uniformly from rows of a full Fourier matrix. After choosing the parameter in (2.1.2) appropriately, we show that...
متن کاملNeuromorphic learning of continuous-valued mappings from noise-corrupted data
The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neuro...
متن کاملRobust learning from bites for data mining
Some methods from statistical machine learning and from robust statistics have two drawbacks. Firstly, they are computer-intensive such that they can hardly be used for massive data sets, say with millions of data points. Secondly, robust and non-parametric confidence intervals for the predictions according to the fitted models are often unknown. Here, we propose a simple but general method to ...
متن کاملExact recoverability from dense corrupted observations via L1 minimization
This paper confirms a surprising phenomenon first observed by Wright et al. [1] [2] under different setting: given m highly corrupted measurements y = AΩ•x + e, where AΩ• is a submatrix whose rows are selected uniformly at random from rows of an orthogonal matrix A and e is an unknown sparse error vector whose nonzero entries may be unbounded, we show that with high probability `1-minimization ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Open Journal of Signal Processing
سال: 2020
ISSN: 2644-1322
DOI: 10.1109/ojsp.2020.3039632