Very Sparse LSSVM Reductions for Large-Scale Data
نویسندگان
چکیده
منابع مشابه
Approximate Model Selection for Large Scale LSSVM
Model selection is critical to least squares support vector machine (LSSVM). A major problem of existing model selection approaches of LSSVM is that the inverse of the kernel matrix need to be calculated with O(n) complexity for each iteration, where n is the number of training examples. It is prohibitive for the large scale application. In this paper, we propose an approximate approach to mode...
متن کاملSparse Reductions for Fixed-Size Least Squares Support Vector Machines on Large Scale Data
Fixed-Size Least Squares Support Vector Machines (FS-LSSVM) is a powerful tool for solving large scale classification and regression problems. FS-LSSVM solves an over-determined system of M linear equations by using Nyström approximations on a set of prototype vectors (PVs) in the primal. This introduces sparsity in the model along with ability to scale for large datasets. But there exists no f...
متن کاملAlgorithms and Data Structures for Very Large Sparse Matrices
Sparse matrix-vector multiplication (SpMV) is one of the most important numerical core methods in scientific and engineering computing. On today’s petascale and future exascale systems, the three principal problems related to SpMV are the minimization of communication between processors in distributed-memory environments, the maximization of the efficiency of local SpMV performed by a single pr...
متن کاملVery Large Scale Visualization Methods for Astrophysical Data
We address the problem of interacting with scenes that contain a very large range of scales. Computer graphics environments normally deal with only a limited range of orders of magnitude before numerical error and other anomalies begin to be apparent, and the effects vary widely from environment to environment. Applications such as astrophysics, where a single scene could in principle contain v...
متن کاملParallelisation of Sparse Grids for Large Scale Data Analysis
Sparse Grids (SG), due to Zenger, are the basis for efficient high dimensional approximation and have recently been applied successfully to predictive modelling. They are spanned by a collection of simpler function spaces represented by regular grids. The combination technique prescribes how approximations on simple grids can be combined to approximate the high dimensional functions. It can be ...
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 Transactions on Neural Networks and Learning Systems
سال: 2015
ISSN: 2162-237X,2162-2388
DOI: 10.1109/tnnls.2014.2333879