Timezone: »
The double descent curve is one of the most intriguing properties of deep neural networks. It contrasts the classical bias-variance curve with the behavior of modern neural networks, occurring where the number of samples nears the number of parameters. In this work, we explore the connection between the double descent phenomena and the number of samples in the deep neural network setting. In particular, we propose a construction which augments the existing dataset by artificially increasing the number of samples. This construction empirically mitigates the double descent curve in this setting. We reproduce existing work on deep double descent, and observe a smooth descent into the overparameterized region for our construction. This occurs both with respect to the model size, and with respect to the number epochs.
Author Information
John Chen (Rice University)
Qihan Wang (Rice University)
Anastasios Kyrillidis (Rice University)
More from the Same Authors
-
2023 : Adaptive Federated Learning with Auto-Tuned Clients »
J. Lyle Kim · Mohammad Taha Toghani · Cesar Uribe · Anastasios Kyrillidis -
2021 Workshop: Beyond first-order methods in machine learning systems »
Albert S Berahas · Anastasios Kyrillidis · Fred Roosta · Amir Gholaminejad · Michael Mahoney · Rachael Tappenden · Raghu Bollapragada · Rixon Crane · J. Lyle Kim -
2020 Workshop: Beyond first order methods in machine learning systems »
Albert S Berahas · Amir Gholaminejad · Anastasios Kyrillidis · Michael Mahoney · Fred Roosta -
2020 Poster: Negative Sampling in Semi-Supervised learning »
John Chen · Vatsal Shah · Anastasios Kyrillidis -
2019 Poster: Compressing Gradient Optimizers via Count-Sketches »
Ryan Spring · Anastasios Kyrillidis · Vijai Mohan · Anshumali Shrivastava -
2019 Oral: Compressing Gradient Optimizers via Count-Sketches »
Ryan Spring · Anastasios Kyrillidis · Vijai Mohan · Anshumali Shrivastava