We analyze continual learning on a sequence of separable linear
classifi...
To better understand catastrophic forgetting, we study fitting an
overpa...
Recent work has highlighted the role of initialization scale in determin...
We provide a detailed asymptotic study of gradient flow trajectories and...
A recent line of work studies overparametrized neural networks in the "k...
We consider the online linear regression problem, where the predictor ve...
We suggest a new idea of Editorial Network - a mixed extractive-abstract...
In the context of Multi Instance Learning, we analyze the Single Instanc...
In extreme classification problems, learning algorithms are required to ...
The goal of a learner, in standard online learning, is to have the cumul...