DeepAI AI Chat

Datasets for Studying Generalization from Easy to Hard Examples

08/13/2021

∙

by Avi Schwarzschild, et al.

∙

University of Maryland

∙

∙

We describe new datasets for studying generalization from easy to hard examples.

Avi Schwarzschild
14 publications
Eitan Borgnia
9 publications
Arjun Gupta
18 publications
Arpit Bansal
10 publications
Zeyad Emam
4 publications
Furong Huang
51 publications
Micah Goldblum
59 publications
Tom Goldstein
129 publications

page 4

page 5

∙ 11/25/2019

Empirical Study of Easy and Hard Examples in CNN Training

Deep Neural Networks (DNNs) generalize well despite their massive size a...

0 Ikki Kishida, et al. ∙

∙ 07/18/2022

Easy Batch Normalization

It was shown that adversarial examples improve object recognition. But w...

0 Arip Asadulaev, et al. ∙

∙ 01/06/2022

Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

In this paper we propose to study generalization of neural networks on s...

22 Alethea Power, et al. ∙

∙ 07/01/1997

A New Look at the Easy-Hard-Easy Pattern of Combinatorial Search Difficulty

The easy-hard-easy pattern in the difficulty of combinatorial search pro...

0 D. L. Mammen, et al. ∙

∙ 11/11/2019

Evaluating Combinatorial Generalization in Variational Autoencoders

We evaluate the ability of variational autoencoders to generalize to uns...

14 Alican Bozkurt, et al. ∙

∙ 10/24/2022

Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data

High model performance, on average, can hide that models may systematica...

6 Nabeel Seedat, et al. ∙

∙ 12/29/2012

Focus of Attention for Linear Predictors

We present a method to stop the evaluation of a prediction process when ...

0 Raphael Pelossof, et al. ∙

Code Repositories

easy-to-hard-data

Pytorch Datasets for Easy-To-Hard

view repo