1 Newton Methods for Fast Solution of Semisupervised Linear SVMs (2009)
Vikas Sindhwani, Sathiya Keerthi
Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In many information...
ABSTRACT Large Scale Semi-supervised Linear SVMs (2009)
Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In many information...
1 Newton Methods for Fast Solution of Semisupervised Linear SVMs (2008)
Vikas Sindhwani, S. Sathiya Keerthi
In this chapter, we present a family of semi-supervised linear support vector classifiers that are designed to handle partially-labeled sparse datasets with possibly very large number of examples and...
Optimization Techniques for Semi-Supervised Support Vector Machines (2008)
Olivier Chapelle, Vikas Sindhwani, Sathiya S. Keerthi, Nello Cristianini
Due to its wide applicability, the problem of semi-supervised classification is attracting increasing attention in machine learning. Semi-Supervised Support Vector Machines (S 3 VMs) are based on...
11 The Geometric Basis of Semi-supervised Learning (2008)
Vikas Sindhwani, Misha Belkin, Partha Niyogi
In this chapter, we present an algorithmic framework for semi-supervised inference based on geometric properties of probability distributions. Our approach brings together Laplacian-based spectral...
Olivier Chapelle, S. Sathiya Keerthi, Vikas Sindhwani
Semi-supervised SVMs (S 3 VM) attempt to learn low-density separators by maximizing the margin over labeled and unlabeled examples. The associated optimization problem is non-convex. To examine the...
Olivier Chapelle, Vikas Sindhwani, S. Sathiya Keerthi
Semi-supervised SVMs (S 3 VM) attempt to learn low-density separators by maximizing the margin over labeled and unlabeled examples. The associated optimization problem is non-convex. To examine the...
S. Sathiya Keerthi, Vikas Sindhwani, Olivier Chapelle
We consider the task of tuning hyperparameters in SVM models based on minimizing a smooth performance validation function, e.g., smoothed k-fold crossvalidation error, using non-linear optimization...
An Efficient Method for Gradient-Based Adaptation of Hyperparameters in SVM Models (2007)
Keerthi, Sathiya, Sindhwani, Vikas, Chapelle, Olivier
We consider the task of tuning hyperparameters in SVM models based on minimizing a smooth performance validation function, e.g., smoothed k-fold cross-validation error, using non-linear optimization...
Branch and Bound for Semi-Supervised Support Vector Machines (2007)
Chapelle, Olivier, Sindhwani, Vikas, Keerthi, Sathiya
Semi-supervised SVMs (S3VM) attempt to learn low-density separators by maximizing the margin over labeled and unlabeled examples. The associated optimization problem is non-convex. To examine the...
Deterministic Annealing for Semi-supervised Kernel Machines (2006)
Sindhwani, Vikas, Keerthi, Sathiya, Chapelle, Olivier
An intuitive approach to utilizing unlabeled data in kernel-based classification algorithms is to simply treat unknown labels as additional optimization variables. For margin-based loss functions,...
Deterministic annealing for semi-supervised kernel machines (2006)
Vikas Sindhwani, S. Sathiya Keerthi, Olivier Chapelle
An intuitive approach to utilizing unlabeled data in kernel-based classification algorithms is to simply treat unknown labels as additional optimization variables. For marginbased loss functions, one...
Mikhail Belkin, Partha Niyogi, Vikas Sindhwani, Peter Bartlett
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that...
Deterministic annealing for semi-supervised kernel machines (2006)
Vikas Sindhwani, S. Sathiya Keerthi, Olivier Chapelle
An intuitive approach to utilizing unlabeled data in kernel-based classification algorithms is to simply treat unknown labels as additional optimization variables. For marginbased loss functions, one...
A co-regularized approach to semi-supervised learning with multiple views (2005)
Vikas Sindhwani, Partha Niyogi
The Co-Training algorithm uses unlabeled examples in multiple views to bootstrap classifiers in each view, typically in a greedy manner, and operating under assumptions of view-independence and...
Linear manifold regularization for large scale semi-supervised learning (2005)
Vikas Sindhwani, Partha Niyogi
The enormous wealth of unlabeled data in many applications of machine learning is beginning to pose challenges to the designers of semi-supervised learning methods. We are interested in developing...
On Manifold Regularization (2005)
Mikhail Belkin, Partha Niyogi, Vikas Sindhwani
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semisupervised framework that...
Beyond the point cloud: from transductive to semi-supervised learning (2005)
Vikas Sindhwani, Partha Niyogi
Due to its occurrence in engineering domains and implications for natural learning, the problem of utilizing unlabeled data is attracting increasing attention in machine learning. A large body of...
Feature selection in MLPs and SVMs based on maximum output information (2004)
Vikas Sindhwani, Subrata Rakshit, Dipti Deodhare, Deniz Erdogmus, Jose Principe, Partha Niyogi
Abstract — We present feature selection algorithms for multilayer
Manifold regularization: A geometric framework for learning from examples (2004)
Mikhail Belkin, Partha Niyogi, Vikas Sindhwani, Peter Bartlett
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised framework that...
On Manifold Regularization Mikhail Belkin (2004)
Partha Niyogi, Vikas Sindhwani
We propose a family of learning algorithms based on a new form of regularization which allows us to incorporate both labeled and unlabeled data in a general-purpose learner. Transductive graph...
Wei Chu, Vikas Sindhwani, Zoubin Ghahramani, S. Sathiya Keerthi
Correlation between instances is often modelled via a kernel function using input attributes of the instances. Relational knowledge can further reveal additional pairwise correlations between...
Wei Chu, Vikas Sindhwani, Zoubin Ghahramani, S. Sathiya Keerthi
Correlation between instances is often modelled via a kernel function using input attributes of the instances. Relational knowledge can further reveal additional pairwise correlations between...