[hpc-announce] CFP: 2nd Workshop on Machine Learning for Computing Systems

[Gamblin, Todd]

### Call For Papers
### 2nd Workshop on Machine Learning for Computing Systems 

November 20, 2020, Atlanta Georgia
Hosted at Supercomputing 2020

### Important Dates 
Submissions Open: May 1, 2020
Submission Deadline: EXTENDED to September 11, 2020
Notifications Sent: October 2, 2020
Camera-ready: October 12, 2020

Submission Link: https://mlcsworkshop.weebly.com/
 
### Workshop Description

The 2nd Workshop on Machine Learning for Computing Systems (MLCS) brings together researchers across machine learning, data science, HPC, and computing systems to discuss the use, development, and rigorous evaluation of data-driven statistical techniques for the management, design, and optimization of large-scale computing systems. This Supercomputing-hosted edition of MLCS provides a venue for a broad and open discussion regarding the use of ML within the HPC domain, with a focus on including researchers, practitioners, and students across disciplines, as well as presentation of peer-reviewed papers. We particularly encourage submissions which include the public release of datasets and/or attempt to reproduce prior studies.
 
### Topics
We are soliciting full papers, short work-in-progress papers, extended abstracts, experience papers, and position papers on the broad theme of data-driven statistical modeling of large-scale computing systems, including but not limited to:

Use of machine learning or data science in the context of better understanding any of the following large-scale computing system issues:
 
- Hardware faults and errors
- Software errors
- Telemetry data (temperature, voltages, cooling apparatus, etc.)
- Power consumption
- Facilities / building control
- Job scheduling
- Filesystem logs
- Syslog or console logs
- Error detection and correction
- Resilience and fault tolerance
- Failure troubleshooting / assistance of human experts
- Assistance of non-expert users
- System security
- Use of interpretable machine learning models for systems-related decision support (including user/human subject studies)
- Modeling techniques incorporating human expert knowledge along with knowledge extracted from data, and/or use of these models to evaluate, confirm, or refute human assumptions
- New or improved machine learning models particularly suited for computing system problems
- Tools, at any stage of development, using data-driven technologies for some aspect of systems monitoring or design
- Experience reports detailing successes and failures of machine learning applied to systems
- Formulations of unsolved data-related systems problems with the potential for machine learning solutions

We especially encourage submissions which include the public release of systems-related datasets for use by the wider research community.
 
### Submission
We solicit full papers, short work-in-progress papers, extended abstracts, experience papers, position papers, and dataset/problem description papers on the broad theme of data-driven statistical modeling of large-scale computing systems.

- Submitted full papers must be no longer than 8 single-spaced 8.5”x11” pages, including figures, tables, and references; in the SC format (two-column format, using 10-point type on 12-point (single-spaced) leading; and a text block 6.5” wide x 9” deep). Author names and affiliations should appear on the front page.

- Submitted short work-in-progress, experience, position, and dataset/problem description papers must be no longer than 4 single-spaced 8.5” x 11” pages, including figures, tables, and references; in the SC format (two-column format, using 10-point type on 12-point (single-spaced) leading; and a text block 6.5” wide x 9” deep). Author names and affiliations should appear on the front page. 

- Submitted extended abstracts must be no longer than 2 single-spaced 8.5” x 11” pages, including figures, tables, and references; in the SC format (two-column format, using 10-point type on 12-point (single-spaced) leading; and a text block 6.5” wide x 9” deep). Author names and affiliations should appear on the front page. 

Submitted contributions should present original theoretical and/or experimental research in any of the areas listed above that has not been previously published, accepted for publication, not currently under review by another conference of journal, or makes significant progress beyond a previously-published version.

Submitted contributions will be peer-reviewed by multiple program committee members, and acceptance decisions will be based on novelty, technical soundness, and relevance to workshop themes.

Accepted contributions will not be formally published, but will be archived on the workshop website.
  
### Contact
Please address communication to: sc-ws-mlcs at info.supercomputing.org