# MOSAIC, acomparison framework for machine learning models

arXiv: https://arxiv.org/abs/2301.12986 · HTML: https://mlsanity.com/paper/2301.12986/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Why does deep and cheap learning work so well?](https://mlsanity.com/paper/1608.08225/) (2016)
- [The power of deeper networks for expressing natural functions](https://mlsanity.com/paper/1705.05502/) (2017)
- [Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research](https://mlsanity.com/paper/1705.05584/) (2017)
- [Universal halting times in optimization and machine learning](https://mlsanity.com/paper/1511.06444/) (2015)

## Abstract (arXiv)

We introduce MOSAIC, a Python program for machine learning models. Our framework is developed with in mind accelerating machine learning studies through making implementing and testing arbitrary network architectures and data sets simpler, faster and less error-prone. MOSAIC features a full execution pipeline, from declaring the models, data and related hyperparameters within a simple configuration file, to the generation of ready-to-interpret figures and performance metrics. It also includes an advanced run management, stores the results within a database, and incorporates several run monitoring options. Through all these functionalities, the framework should provide a useful tool for researchers, engineers, and general practitioners of machine learning.