# Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning

arXiv: https://arxiv.org/abs/2107.06946 · HTML: https://mlsanity.com/paper/2107.06946/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 14 Jul 2021.

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

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [Distributional Reinforcement Learning with Quantile Regression](https://mlsanity.com/paper/1710.10044/) (2017)
- [Can Federated Learning Save The Planet?](https://mlsanity.com/paper/2010.06537/) (2020)
- [Energy Usage Reports: Environmental awareness as part of algorithmic accountability](https://mlsanity.com/paper/1911.08354/) (2019)
- [Privacy-preserving Q-Learning with Functional Noise in Continuous State Spaces](https://mlsanity.com/paper/1901.10634/) (2019)

## Built on by (most cited first, 8 of 8)

- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning](https://mlsanity.com/paper/2302.08476/) (2023)
- [Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey](https://mlsanity.com/paper/2505.01821/) (2025)
- [FedZero: Leveraging Renewable Excess Energy in Federated Learning](https://mlsanity.com/paper/2305.15092/) (2023)
- [Energy and Carbon Considerations of Fine-Tuning BERT](https://mlsanity.com/paper/2311.10267/) (2023)
- [Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models](https://mlsanity.com/paper/2502.05610/) (2025)
- [Green Federated Learning](https://mlsanity.com/paper/2303.14604/) (2023)
- [Evaluating the Energy Consumption of Machine Learning: Systematic Literature Review and Experiments](https://mlsanity.com/paper/2408.15128/) (2024)

## Abstract (arXiv)

In recent years, machine learning techniques utilizing large-scale datasets have achieved remarkable performance. Differential privacy, by means of adding noise, provides strong privacy guarantees for such learning algorithms. The cost of differential privacy is often a reduced model accuracy and a lowered convergence speed. This paper investigates the impact of differential privacy on learning algorithms in terms of their carbon footprint due to either longer run-times or failed experiments. Through extensive experiments, further guidance is provided on choosing the noise levels which can strike a balance between desired privacy levels and reduced carbon emissions.