research
∙
06/06/2023
Continual Learning in Linear Classification on Separable Data
We analyze continual learning on a sequence of separable linear classifi...
share
research
∙
05/19/2022
How catastrophic can catastrophic forgetting be in linear regression?
To better understand catastrophic forgetting, we study fitting an overpa...
research
∙
02/19/2021
On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
Recent work has highlighted the role of initialization scale in determin...
research
∙
07/13/2020
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy
We provide a detailed asymptotic study of gradient flow trajectories and...
research
∙
02/20/2020
Kernel and Rich Regimes in Overparametrized Models
A recent line of work studies overparametrized neural networks in the "k...
research
∙
06/13/2019
Variance Estimation For Online Regression via Spectrum Thresholding
We consider the online linear regression problem, where the predictor ve...
research
∙
02/27/2019
An Editorial Network for Enhanced Document Summarization
We suggest a new idea of Editorial Network - a mixed extractive-abstract...
research
∙
12/17/2018
Multi Instance Learning For Unbalanced Data
In the context of Multi Instance Learning, we analyze the Single Instanc...
research
∙
03/08/2018
Efficient Loss-Based Decoding On Graphs For Extreme Classification
In extreme classification problems, learning algorithms are required to ...
research
∙
03/01/2013