# Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration

arXiv: https://arxiv.org/abs/2002.03875 · HTML: https://mlsanity.com/paper/2002.03875/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2020.

## Built on by (most cited first, 6 of 6)

- [A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness](https://mlsanity.com/paper/2106.09129/) (2021)
- [Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks](https://mlsanity.com/paper/2303.11338/) (2023)
- [Calibrating the Rigged Lottery: Making All Tickets Reliable](https://mlsanity.com/paper/2302.09369/) (2023)
- [Uncovering the Hidden Cost of Model Compression](https://mlsanity.com/paper/2308.14969/) (2023)
- [Quantifying lottery tickets under label noise: accuracy, calibration, and complexity](https://mlsanity.com/paper/2306.12190/) (2023)
- [Lottery Tickets Are Not Deployment Tickets](https://mlsanity.com/paper/2607.27031/) (2026)

## Abstract (arXiv)

The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled efficient inferencing. Supervised models with uncalibrated confidences tend to be overconfident even when making wrong prediction. In this paper, for the first time, we study how explicit confidence calibration in the over-parameterized network impacts the quality of the resulting lottery tickets. More specifically, we incorporate a suite of calibration strategies, ranging from mixup regularization, variance-weighted confidence calibration to the newly proposed likelihood-based calibration and normalized bin assignment strategies. Furthermore, we explore different combinations of architectures and datasets, and make a number of key findings about the role of confidence calibration. Our empirical studies reveal that including calibration mechanisms consistently lead to more effective lottery tickets, in terms of accuracy as well as empirical calibration metrics, even when retrained using data with challenging distribution shifts with respect to the source dataset.