collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG20213 cited

Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond

Negin Majidi, Ehsan Amid, Hossein Talebi +1

Many learning tasks in machine learning can be viewed as taking a gradient step towards minimizing the average loss of a batch of examples in each training iteration. When noise is…

cs.LG2020

A case where a spindly two-layer linear network whips any neural network with a fully connected input layer

Manfred K. Warmuth, Wojciech Kotłowski, Ehsan Amid

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…

cs.LG2020

Reparameterizing Mirror Descent as Gradient Descent

Ehsan Amid, Manfred K. Warmuth

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 upda…

cs.LG2019

An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint

Ehsan Amid, Manfred K. Warmuth

We shed new insights on the two commonly used updates for the online -PCA problem, namely, Krasulina's and Oja's updates. We show that Krasulina's update corresponds to a projec…

cs.LG2019

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

Ehsan Amid, Manfred K. Warmuth, Rohan Anil +1

We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the l…

cs.LG2019

Divergence-Based Motivation for Online EM and Combining Hidden Variable Models

Ehsan Amid, Manfred K. Warmuth

Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the…