# Cello: Efficient Computer Systems Optimization with Predictive Early Termination and Censored Regression

arXiv: https://arxiv.org/abs/2204.04831 · HTML: https://mlsanity.com/paper/2204.04831/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 87 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [A Tutorial on Bayesian Optimization](https://mlsanity.com/paper/1807.02811/) (2018)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [Freeze-Thaw Bayesian Optimization](https://mlsanity.com/paper/1406.3896/) (2014)
- [Survival regression with accelerated failure time model in XGBoost](https://mlsanity.com/paper/2006.04920/) (2020)
- [Practical Design Space Exploration](https://mlsanity.com/paper/1810.05236/) (2018)
- [Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning](https://mlsanity.com/paper/2109.12021/) (2021)
- [Stopping criteria for boosting automatic experimental design using real-time fMRI with Bayesian optimization](https://mlsanity.com/paper/1511.07827/) (2015)
- [Bayesian Optimization With Censored Response Data](https://mlsanity.com/paper/1310.1947/) (2013)
- [A neural network memory prefetcher using semantic locality](https://mlsanity.com/paper/1804.00478/) (2018)
- [A Survey of Machine Learning Applied to Computer Architecture Design](https://mlsanity.com/paper/1909.12373/) (2019)
- [Neural Model-based Optimization with Right-Censored Observations](https://mlsanity.com/paper/2009.13828/) (2020)
- [BayesPerf: Minimizing Performance Monitoring Errors Using Bayesian Statistics](https://mlsanity.com/paper/2102.10837/) (2021)

## Abstract (arXiv)

Sample-efficient machine learning (SEML) has been widely applied to find optimal latency and power tradeoffs for configurable computer systems. Instead of randomly sampling from the configuration space, SEML reduces the search cost by dramatically reducing the number of configurations that must be sampled to optimize system goals (e.g., low latency or energy). Nevertheless, SEML only reduces one component of cost -- the total number of samples collected -- but does not decrease the cost of collecting each sample. Critically, not all samples are equal; some take much longer to collect because they correspond to slow system configurations. This paper present Cello, a computer systems optimization framework that reduces sample collection costs -- especially those that come from the slowest configurations. The key insight is to predict ahead of time whether samples will have poor system behavior (e.g., long latency or high energy) and terminate these samples early before their measured system behavior surpasses the termination threshold, which we call it predictive early termination. To predict the future system behavior accurately before it manifests as high runtime or energy, Cello uses censored regression to produces accurate predictions for running samples. We evaluate Cello by optimizing latency and energy for Apache Spark workloads. We give Cello a fixed amount of time to search a combined space of hardware and software configuration parameters. Our evaluation shows that compared to the state-of-the-art SEML approach in computer systems optimization, Cello improves latency by 1.19X for minimizing latency under a power constraint, and improves energy by 1.18X for minimizing energy under a latency constraint.