Privacy Aware Learning
We study statistical risk minimization problems under a privacy model in which the data is kept confidential even from the learner. In this local privacy framework, we establish...
Publications
Explore 317 academic publications
Showing 12 of
317 publications
Preconditioning of Truncated-Newton Methods
In this paper we discuss the use of truncated-Newton methods, a flexible class of iterative methods, in the solution of large-scale unconstrained minimization problems. At each ...
Neural networks for routing communication traffic
The use of neural network computational algorithms to determine optimal traffic routing for communication networks is introduced. The routing problem requires choosing multilink...
Solving Variational Inequalities with Stochastic Mirror-Prox Algorithm
In this paper we consider iterative methods for stochastic variational inequalities (s.v.i.) with monotone operators. Our basic assumption is that the operator possesses both sm...
A General-Purpose Version of the Fast Decoupled Loadflow
A new version of the fast decoupled load flow, in which a more broad range of power systems can be solved, is presented. The key lies in the different way in which the resistanc...
On the degrees of freedom in shape-restricted regression
For the problem of estimating a regression function, $\\mu$ say,\nsubject to shape constraints, like monotonicity or convexity, it is argued that\nthe divergence of the maximum ...
A general-purpose version of the fast decoupled load flow
A new version of the fast decoupled load flow, in which a more broad range of power systems can be solved, is presented. The key lies in the different way in which the resistanc...
On the Convergence of a New Conjugate Gradient Algorithm
This paper studies the convergence of a conjugate gradient algorithm proposed in a recent paper by Shanno. It is shown that under loose step length criteria similar to but sligh...
Generalized Bradley-Terry Models and Multi-Class Probability Estimates
The Bradley-Terry model for obtaining individual skill from paired comparisons has been popular in many areas. In machine learning, this model is related to multi-class probabil...
Millimeter‐scale genetic gradients and community‐level molecular convergence in a hypersaline microbial mat
To investigate the extent of genetic stratification in structured microbial communities, we compared the metagenomes of 10 successive layers of a phylogenetically complex hypers...