1:30 PM - 1:50 PM
[2D4-GS-2-01] Proposed learning method assuming distribution shift due to corrupted data
Keywords:Image Classification, Deep Learning, Distributionally Robust Optimization
Even in tasks in which deep learning excels, such as image classification, if the strength of the noise in the training
data is uneven, the average loss minimization of conventional methods will result in a significant bias toward good or
bad classification. SharpDRO, which considers the flatness and distribution shift of the objective function at once,
has been proposed as a method that preserves the generalization ability of deep learning while targeting diverse
data for learning, but its practicality is limited by its dependence on prior knowledge and increased computational
cost. In this proposal, the ”flooding” of the loss is applied to the objective function of DRO instead of the average
loss, leading to the same effect as SharpDRO with the same computational cost as the usual gradient descent
method.
data is uneven, the average loss minimization of conventional methods will result in a significant bias toward good or
bad classification. SharpDRO, which considers the flatness and distribution shift of the objective function at once,
has been proposed as a method that preserves the generalization ability of deep learning while targeting diverse
data for learning, but its practicality is limited by its dependence on prior knowledge and increased computational
cost. In this proposal, the ”flooding” of the loss is applied to the objective function of DRO instead of the average
loss, leading to the same effect as SharpDRO with the same computational cost as the usual gradient descent
method.
Authentication for paper PDF access
A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.