In the field of optimal transport, two prominent subfields face each oth...
Training algorithms, broadly construed, are an essential part of every d...
One of the most popular ML algorithms, AdaBoost, can be derived from the...
While deep learning has unlocked advances in computational biology once
...
The link with exponential families has allowed k-means clustering to be
...
In this work, we propose a novel approach for layerwise representation
l...
Recent work has designed methods to demonstrate that model updates in AS...
We present the surprising result that randomly initialized neural networ...
Optimizers like Adam and AdaGrad have been very successful in training
l...
Multi-task learning can leverage information learned by one task to bene...
We study a local loss construction approach for optimizing neural networ...
Many learning tasks in machine learning can be viewed as taking a gradie...
We consider a wireless federated learning system where multiple data hol...
Conducting pairwise comparisons is a widely used approach in curating hu...
Multi-task learning can leverage information learned by one task to bene...
It was conjectured that any neural network of any structure and arbitrar...
Continuous-time mirror descent (CMD) can be seen as the limit case of th...
We introduce "TriMap"; a dimensionality reduction technique based on
tri...
We shed new insights on the two commonly used updates for the online k-P...
We introduce a temperature into the exponential function and replace the...
Expectation-Maximization (EM) is the fallback method for parameter estim...
We first show that the commonly used dimensionality reduction (DR) metho...
We develop a variant of multiclass logistic regression that achieves thr...
We describe a new method called t-ETE for finding a low-dimensional embe...