Contributing

We are encouraging contributions that present original unpublished research. Submissions (up to 12 pages) should adhere to the single-column LNCS style (http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0). Topics of interest include but are not limited to the following topic areas:

  • Scientific data set creation, ingest, curation, labelling, and analysis with statistical models and inference

  • Incorporating realtime and ad-hoc data analytics into applications and their deployment on supercomputing and cluster platforms

  • Computational steering through machine learning models and related control theory approaches

  • Meta-data and data metrics collection and generation for large data collections and output data sets of computational simulations

  • Multi-precision training/inference methods and their use on modern hardware for simulation data

  • Novel use of discriminative and generative machine learning approaches for scientific data sets including Adversarial and Reinforcement Learning with self-supervision

  • Modern HPC storage issues when dealing with integration of computational simulation outputs with data analytics software

  • Synchronous and asynchronous learning approaches at scale for methods related to deep neural network training, stochastic gradient descent, loss-function engineering, and related distributed optimization techniques

  • Model derivation and training for scalable simulations and data sets

  • Hyperparameter search and optimization incorporating recent advances in Bayesian optimization

  • Deployment of statistical models and their implementations such as TensorFlow and PyTorch or application-specific tensor frameworks.

  • Integration of models with large scale simulations code bases through containers (Kubernetes, Docker, Singularity, OpenShift), virtualizaiton, colocation, and workflow frameworks

Additional Submission Format

We also intent to implement a unique format for submitting workshop contributions: given the increasing relevance of sustainable software development and open source community process, and acknowledging many of the contributions in 2019 promoting software solutions, we will allow for software submissions based on community-reviewed pull requests. Specifically, authors can submit software contributions featuring detailed software documentation, effectiveness and performance analysis by pointing to a community-reviewed pull request in a versioning system. We will complement the software review with a blind review assessing the contribution’s innovation level and community benefit, and decide on both, scientific and software quality upon the acceptance of the contribution. This workflow was recently proposed as a modern peer-reviewing concept for computer-based research. Both, traditional contributions and software-based contributions can be submitted to SDASC, and accepted contributions will be presented at the half-day workshop and included in the post-conference proceedings.

Conference Logistics and Proceedings

The authors of accepted contributions will get a 30 minute time slot during the workshop to present their work. The revised versions of accepted papers will be published as post-conference proceedings. This year, the ISC workshop chairs organize a joint Workshop Proceedings that will be published with Springer similar to the ISC 2020 research papers proceedings. The workshop proceedings will be published after the conference but we will collect preliminary versions of the papers and make them available during the workshop to your workshop attendees.