BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220812T074357Z
LOCATION:Singapore Room
DTSTART;TZID=Europe/Stockholm:20220629T110000
DTEND;TZID=Europe/Stockholm:20220629T130000
UID:submissions.pasc-conference.org_PASC22_sess156@linklings.com
SUMMARY:MS5D - High-Performance Machine Learning: Scale and Performance (P
 art I)
DESCRIPTION:Minisymposium\n\nWith the growing range of machine learning ap
 proaches and the availability of large-scale data, performant and scalable
  algorithmic techniques have become central topics. Nowadays, high-perform
 ance computing (HPC) technologies have become essential for modern large-s
 cale machine learning applications. The convergence of HPC and machine lea
 rning has shown compelling success across many application fields. With th
 at said, real-world applications are rife with inherent challenges associa
 ted with high dimensionality, scarcity of data, and ill-posedness, among m
 any others. This minisymposium will serve as a platform to discuss cutting
 -edge developments for modern, scalable, and efficient machine learning ap
 proaches.\n\nFourCastNet - An Example DL Architecture for Scaling Deep Lea
 rning Applications to Large HPC Systems\n\nKurth, Messmer\n\nWe are going 
 to present the challenges of scaling deep learning applications to large H
 PC systems on the example of FourCastNet.FourCastNet is a Fourier Neural O
 perator (FNO) based neural network which employs spectral convolutions to 
 generate competitive weather predictions for up to 8 days into th...\n\n--
 -------------------\nRACE: Speeding up Spectral Clustering and Iterative S
 olvers using Level-Based Parallelization and Blocking Techniques\n\nAlappa
 t, Pasadakis, Hager, Schenk, Wellein\n\nClustering and linear iterative so
 lvers are indispensable for large-scale simulations in the area of machine
  learning and mathematical optimization. In this talk, we present methods 
 to accelerate existing spectral clustering techniques and solvers by using
  the concept of levels as developed in the c...\n\n---------------------\n
 Sparse Quadratic Approximation for Graph Learning\n\nPasadakis, Bollhöfer,
  Schenk\n\nIn this talk we address the problem of learning large graphs<br
  />represented by M-matrices via an $\ell_1$-regularized <br />Gaussian ma
 ximum-likelihood approach. We build on top of a<br />state-of-the-art spar
 se precision matrix estimation package and<br />introduce two algorithms t
 hat learn M-mat...\n\n---------------------\nParallelized Integrated Neste
 d Laplace Approximations for Fast Bayesian Inference\n\nGaedke-Merzhäuser,
  Rue, Schenk\n\nBayesian computing has been on the rise for years due to i
 ts ability to make reliable predictions using flexible yet interpretable m
 odelling frameworks, while also providing uncertainty estimates for all pa
 rameters in the form of distributions. For more complex models, performing
  the Bayesian infere...\n\n\nDomain: Computer Science and Applied Mathemat
 ics
END:VEVENT
END:VCALENDAR