Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Tim Marrinan

Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Oct 01, 2023
Sinjini Banerjee, Reilly Cannon, Tim Marrinan, Tony Chiang, Anand D. Sarwate

Figure 1 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Figure 2 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Figure 3 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Figure 4 for Robust Nonparametric Hypothesis Testing to Understand Variability in Training Neural Networks

Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model. Several works suggest this variability is negligible when models have the same performance, which in the case of classification is test accuracy. However, models with similar test accuracy may not be computing the same function. We propose a new measure of closeness between classification models based on the output of the network before thresholding. Our measure is based on a robust hypothesis-testing framework and can be adapted to other quantities derived from trained models.

Via

Access Paper or Ask Questions