We introduce new Perceptron-based algorithms for the online multitask binary classification
problem. Under suitable regularity conditions, our algorithms are shown to improve on their …

Most of the recent successful applications of neural networks have been based on training
with gradient descent updates. However, for some small networks, other mirror descent …

Sparse linear problems can be learned well with online multiplicative updates. The question
is weather there are closed form updates based on the past examples that can sample …

It is known that the solution of regularization and interpolation problems with Hilbertian
penalties can be expressed as a linear combination of the data. This very useful property …

We give an online algorithm and prove novel mistake and regret bounds for online binary
matrix completion with side information. The mistake bounds we prove are of the form\tilde …

The representer theorem assures that kernel methods retain optimality under penalized
empirical risk minimization. While a sufficient condition on the form of the regularizer …

Some of the simplest loss functions considered in Machine Learning are the square loss, the
logistic loss and the hinge loss. The most common family of algorithms, including Gradient …

It was conjectured that any neural network of any structure and arbitrary differentiable
transfer functions at the nodes cannot learn the following problem sample efficiently when …

This thesis considers the problem of binary matrix completion with side information in the
online setting and the applications thereof. The side information provides additional …

Bregman divergence is an important class of divergence functions in Machine Learning.
Many well-known updates including gradient descent and (un) normalized exponentiated …