Recent advances have seen the proliferation of GPUs and multicore computers as well as the development of new libraries that fully exploit the new hardware capabilities. On the algorithmic side, the increased demand for processing large-scale and structured datasets has stimulating the development of new solutions as well as leading to the revival of old scalable and distributed algorithms, including proximal, stochastic and generalized Frank-Wolfe methods.
The workshop will provide a venue for researchers and practitioners to interact on the latest developments in technical computing in relation to machine learning and mathematical engineering problems and methods (including also optimization, system identification, computational statistics, signal processing, data visualization, deep learning, compressed sensing and big-data). A special attention will be paid to implementations on high-level high-performance modern programming languages suitable for large-scale, parallel and distributed computing and capable to efficiently handle structured data. The emphasis is especially on the open-source alternatives, including but not limited to Julia, Python, Scala and R.
The 3 days main event (8-10 September) will consist of invited and contributed talks as well as poster presentations. It will be followed by a 2 days additional event (11-12 September) including software demos and hands-on tutorials on selected topics. Attendees can register to the main event only or to the full workshop.Additional details will be announced shortly.