vix.ing · top · new · best · stats · spec

DSD2: Can We Dodge Sparse Double Descent and Compress the Neural Network Worry-Free?

2023/03/02 by Victor Quétu, Quétu, Victor, Enzo Tartaglione +1
Computer Science · #Computational Physics and Python Applications #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2303.01213

openalex publication_date 2023/03/02 · openalex created_date 2023/03/05 · openalex updated_date 2026/07/28

Abstract

Neoteric works have shown that modern deep learning models can exhibit a sparse double descent phenomenon. Indeed, as the sparsity of the model increases, the test performance first worsens since the model is overfitting the training data; then, the overfitting reduces, leading to an improvement in performance, and finally, the model begins to forget critical information, resulting in underfitting. Such a behavior prevents using traditional early stop criteria. In this work, we have three key contributions. First, we propose a learning framework that avoids such a phenomenon and improves generalization. Second, we introduce an entropy measure providing more insights into the insurgence of this phenomenon and enabling the use of traditional stop criteria. Third, we provide a comprehensive quantitative analysis of contingent factors such as re-initialization methods, model width and depth, and dataset noise. The contributions are supported by empirical evidence in typical setups. Our code is available at https://github.com/VGCQ/DSD2.

Related