`

Timezone: »

 
Personalized Benchmarking with the Ludwig Benchmarking Toolkit
Avanika Narayan · Piero Molino · Karan Goel · Willie Neiswanger · Chris Ré

The rapid proliferation of machine learning models across domains and deployment settings has given rise to various communities (e.g. industry practitioners) which seek to benchmark models across tasks and objectives of personal value. Unfortunately, these users cannot use standard benchmark results to perform such value-driven comparisons, as traditional benchmarks evaluate models on a single objective (e.g. average accuracy) and don’t facilitate a standardized training framework that controls for confounding variables (e.g. computational budget), making fair comparisons difficult. To address these challenges, we introduce the open-source Ludwig Benchmarking Toolkit (LBT), a personalized benchmarking toolkit for running end-to-end benchmark studies (from hyperparameter optimization to evaluation) across an easily extensible set of tasks, deep learning models, datasets and evaluation metrics. LBT provides a configurable interface for customizing evaluation and controlling training, a standardized training framework for eliminating confounding variables, and support for multi-objective evaluation. We demonstrate how LBT can be used to create personalized benchmark-studies with a large-scale comparative analysis for text classification across 7 models and 9 datasets. We explore the trade-offs between inference latency and performance, relationships between dataset attributes and performance, and the effects of pretraining on convergence and robustness, showing how LBT can be used to satisfy various benchmarking objectives.

Author Information

Avanika Narayan (Stanford University)
Piero Molino (Uber AI Labs)
Karan Goel (Stanford University)
Willie Neiswanger (Stanford University)
Chris Ré (Stanford)

More from the Same Authors