Consistency analysis of spectral regularization algorithms (Q437553): Difference between revisions

Summary: We investigate the consistency of spectral regularization algorithms. We generalize the usual definition of regularization function to enrich the content of spectral regularization algorithms. Under a more general prior condition, using refined error decompositions and techniques of operator norm estimation, satisfactory error bounds and learning rates are proved.

0 references

Mathematics Subject Classification ID

68T05

0 references

zbMATH DE Number

6058113

0 references

MaRDI profile type

MaRDI publication profile

0 references

Wikidata QID

Q58695157

0 references

full work available at URL

https://doi.org/10.1155/2012/436510

0 references

OpenAlex ID

W1974628717

0 references

cites work

On regularization algorithms in learning theory

0 references

Least square regression with indefinite kernels and coefficient regularization

0 references

Spectral Algorithms for Supervised Learning

0 references

On the mathematical foundations of learning

0 references

Regularization networks and support vector machines

0 references

Q4826695

0 references

Learning theory estimates via integral operators and their approximations

0 references

A note on application of integral operator in learning theory

0 references

Regularized least square regression with dependent samples

0 references

Learning rates of least-square regularized regression

0 references

Leave-One-Out Bounds for Kernel Methods

0 references

Q4261789

0 references

Learning with sample dependent hypothesis spaces

0 references

On early stopping in gradient descent learning

0 references

Application of integral operator for regularized least-square regression

0 references

Q3667432

0 references

Optimum bounds for the distributions of martingales in Banach spaces

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:437553

@@ Property / author @@
-Hongwei Sun
@@ Property / author: Hongwei Sun / rank @@
-Normal rank
@@ Property / author @@
+Hongwei Sun
@@ Property / author: Hongwei Sun / rank @@
+Normal rank
@@ Property / review text @@
+Summary: We investigate the consistency of spectral regularization algorithms. We generalize the usual definition of regularization function to enrich the content of spectral regularization algorithms. Under a more general prior condition, using refined error decompositions and techniques of operator norm estimation, satisfactory error bounds and learning rates are proved.
+Normal rank
@@ Property / Mathematics Subject Classification ID @@
+T05
@@ Property / Mathematics Subject Classification ID: 68T05 / rank @@
+Normal rank
@@ Property / zbMATH DE Number @@
+6058113
@@ Property / zbMATH DE Number: 6058113 / rank @@
+Normal rank
@@ Property / MaRDI profile type @@
+MaRDI publication profile
@@ Property / MaRDI profile type: MaRDI publication profile / rank @@
+Normal rank
@@ Property / Wikidata QID @@
+Q58695157
@@ Property / Wikidata QID: Q58695157 / rank @@
+Normal rank
@@ Property / full work available at URL @@
+https://doi.org/10.1155/2012/436510
+Normal rank
@@ Property / OpenAlex ID @@
+W1974628717
@@ Property / OpenAlex ID: W1974628717 / rank @@
+Normal rank
@@ Property / cites work @@
+On regularization algorithms in learning theory
@@ Property / cites work: On regularization algorithms in learning theory / rank @@
+Normal rank
@@ Property / cites work @@
+Least square regression with indefinite kernels and coefficient regularization
+Normal rank
@@ Property / cites work @@
+Spectral Algorithms for Supervised Learning
@@ Property / cites work: Spectral Algorithms for Supervised Learning / rank @@
+Normal rank
@@ Property / cites work @@
+On the mathematical foundations of learning
@@ Property / cites work: On the mathematical foundations of learning / rank @@
+Normal rank
@@ Property / cites work @@
+Regularization networks and support vector machines
+Normal rank
@@ Property / cites work @@
+Q4826695
@@ Property / cites work: Q4826695 / rank @@
+Normal rank
@@ Property / cites work @@
+Learning theory estimates via integral operators and their approximations
+Normal rank
@@ Property / cites work @@
+A note on application of integral operator in learning theory
+Normal rank
@@ Property / cites work @@
+Regularized least square regression with dependent samples
+Normal rank
@@ Property / cites work @@
+Learning rates of least-square regularized regression
+Normal rank
@@ Property / cites work @@
+Leave-One-Out Bounds for Kernel Methods
@@ Property / cites work: Leave-One-Out Bounds for Kernel Methods / rank @@
+Normal rank
@@ Property / cites work @@
+Q4261789
@@ Property / cites work: Q4261789 / rank @@
+Normal rank
@@ Property / cites work @@
+Learning with sample dependent hypothesis spaces
@@ Property / cites work: Learning with sample dependent hypothesis spaces / rank @@
+Normal rank
@@ Property / cites work @@
+On early stopping in gradient descent learning
@@ Property / cites work: On early stopping in gradient descent learning / rank @@
+Normal rank
@@ Property / cites work @@
+Application of integral operator for regularized least-square regression
+Normal rank
@@ Property / cites work @@
+Q3667432
@@ Property / cites work: Q3667432 / rank @@
+Normal rank
@@ Property / cites work @@
+Optimum bounds for the distributions of martingales in Banach spaces
+Normal rank
@@ links / mardi / name / links / mardi / name @@
+Publication:437553