Optimization in machine learning, both theoretical and applied, is prese...
We introduce a binary embedding framework, called Proximity Preserving C...
In human perception and cognition, the fundamental operation that brains...
We study the interplay between memorization and generalization of
overpa...
Understanding learning and generalization of deep architectures has been...
The (stochastic) gradient descent and the multiplicative update method a...
Adaptive gradient-based optimizers such as AdaGrad and Adam are among th...
We study the complexity of the entire regularization path for least squa...
Preconditioned gradient methods are among the most general and powerful ...
We describe a framework for deriving and analyzing online optimization
a...
We develop a general duality between neural networks and compositional
k...
We show that parametric models trained by a stochastic gradient method (...
Object recognition and localization are important tasks in computer visi...
This paper re-examines the problem of parameter estimation in Bayesian
n...
A constant rebalanced portfolio is an asset allocation algorithm which k...
Matrix approximation is a common tool in machine learning for building
a...