Publications

Function-as-a-Service (FaaS) has raised a growing interest in how to “tame” serverless computing to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems have been implemented for training ML models. Certainly, these research articles are significant steps in the correct direction. However, they do not completely answer the nagging question of when serverless ML training can be more cost-effective compared to traditional “serverful” computing. To help in this endeavor, we propose MLLess, a FaaS-based ML training prototype built atop IBM Cloud Functions. To boost cost-efficiency, MLLess implements two innovative optimizations tailored to the traits of serverless computing: on one hand, a significance filter, to make indirect communication more effective, and on the other hand, a scale-in auto-tuner, to reduce cost by benefiting from the FaaS sub-second billing model (often per 100 ms). Our results certify that MLLess can be 15X faster than serverful ML systems at a lower cost for sparse ML models that exhibit fast convergence such as sparse logistic regression and matrix factorization. Furthermore, our results show that MLLess can easily scale out to increasingly large fleets of serverless workers.

@article{gimeno2024mlless,
  title     = {{MLLess}: Achieving cost efficiency in serverless machine learning training},
  author    = {Gimeno Sarroca, Pablo and S{\'a}nchez-Artigas, Marc},
  journal   = {Journal of Parallel and Distributed Computing},
  volume    = {183},
  pages     = {104764},
  publisher = {Elsevier},
  year      = {2024},
  doi       = {10.1016/j.jpdc.2023.104764}
}

Despite that Function-as-a-Service (FaaS) has settled down as one of the fundamental cloud programming models, it is still evolving quickly. Recently, Amazon has introduced S3 Object Lambda, which allows a user-defined function to be automatically invoked to process an object as it is being downloaded from S3. As with any new feature, careful study thereof is the key to elucidate if S3 Object Lambda, or more generally, if inline serverless data processing, is a valuable addition to the cloud. For this reason, we conduct an extensive measurement study of this novel service, in order to characterize its architecture and performance (in terms of coldstart latency, TTFB times, and more). We particularly put an eye on the streaming capabilities of this new form of function, as it may open the door to empower existing serverless systems with stream processing capacities. We discuss the pros and cons of this new capability through several workloads, concluding that S3 Object Lambda can go far beyond its original purpose and be leveraged as a building block for more complex abstractions.

@inproceedings{gimeno2023objectlambda,
  title     = {On Data Processing through the Lenses of {S3} Object Lambda},
  author    = {Gimeno Sarroca, Pablo and S{\'a}nchez-Artigas, Marc},
  booktitle = {IEEE INFOCOM 2023 - IEEE Conference on Computer Communications},
  address   = {New York City, NY, USA},
  pages     = {1--10},
  publisher = {IEEE},
  year      = {2023},
  doi       = {10.1109/INFOCOM53939.2023.10228890}
}

Function-as-a-Service (FaaS) has raised a growing interest in how to "tame" serverless to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems have been implemented for training ML models. Certainly, these research articles are significant steps in the correct direction. However, they do not completely answer the nagging question of when serverless ML training can be more cost-effective compared to traditional "serverful" computing. To help in this task, we propose MLLess, a FaaS-based ML training prototype built atop IBM Cloud Functions. To boost cost-efficiency, MLLess implements two key optimizations: a significance filter and a scale-in auto-tuner, and leverages them to specialize model training to the FaaS model. Our results certify that MLLess can be 15X faster than serverful ML systems at a lower cost for ML models (such as sparse logistic regression and matrix factorization) that exhibit fast convergence.

@inproceedings{sanchez2021mlless,
  title     = {Experience Paper: Towards enhancing cost efficiency in serverless machine learning training},
  author    = {S{\'a}nchez-Artigas, Marc and Gimeno Sarroca, Pablo},
  booktitle = {Proceedings of the 22nd International Middleware Conference},
  address   = {Qu{\'e}bec City, Canada},
  pages     = {210--222},
  publisher = {ACM},
  year      = {2021},
  doi       = {10.1145/3464298.3494884}
}

Early Mobilisation routines aim at improving the recovery process of critically ill patients that are hospitalised in intensive care units. Such routines consist of passive and active progressive mobilisations aiming at reducing the side-effects derived from ICU stays. In this paper, we present e-PEMICU, an e-health platform to support early mobilisation programmes in intensive care units. Our solution is founded on motion sensors and smartphones, hence, it is affordable and easy to deploy in real scenarios. We present the design and implementation of a prototype that has been created to address real users needs. Our platform paves the way for a better and sustainable application of current early mobilisation routines.

@inproceedings{martinez2019epemicu,
  title     = {e-{PEMICU}: an e-Health Platform to Support Early Mobilisation in Intensive Care Units},
  author    = {Mart{\'i}nez-Ballest{\'e}, Antoni and Gimeno, Pablo and Marin{\'e}, Aleix and Batista, Edgar and Solanas, Agusti},
  booktitle = {2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)},
  address   = {Patras, Greece},
  pages     = {1--6},
  publisher = {IEEE},
  year      = {2019},
  doi       = {10.1109/IISA.2019.8900718}
}