The reviewed record of science sign in
Pith

arxiv: 2404.04111 · v1 · pith:GFSKIOYK · submitted 2024-04-05 · cs.LG

The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:GFSKIOYKrecord.jsonopen to challenge →

classification cs.LG
keywords discardingepochsneuraltechniquesearlylearningnumberperformance
0
0 comments X
read the original abstract

To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations of neural networks. Early discarding techniques limit the resources granted to unpromising candidates by observing the empirical learning curves and canceling neural network training as soon as the lack of competitiveness of a candidate becomes evident. Despite two decades of research, little is understood about the trade-off between the aggressiveness of discarding and the loss of predictive performance. Our paper studies this trade-off for several commonly used discarding techniques such as successive halving and learning curve extrapolation. Our surprising finding is that these commonly used techniques offer minimal to no added value compared to the simple strategy of discarding after a constant number of epochs of training. The chosen number of epochs depends mostly on the available compute budget. We call this approach i-Epoch (i being the constant number of epochs with which neural networks are trained) and suggest to assess the quality of early discarding techniques by comparing how their Pareto-Front (in consumed training epochs and predictive performance) complement the Pareto-Front of i-Epoch.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data

    cs.CV 2026-06 unverdicted novelty 6.0

    FLORA is an octree-based deep learning framework with auxiliary data fusion that predicts forest attributes from heterogeneous LiDAR, achieving rRMSE of 12.3% for dominant height and 39% for total volume on 32k French...