Proxima

Abstract

Atomistic-scale simulations are prominent scientific applications that require the repetitive execution of a computationally expensive routine to calculate a system's potential energy. Prior work shows that these expensive routines can be replaced with a machinelearned surrogate approximation to accelerate the simulation at the expense of the overall accuracy. The exact balance of speed and accuracy depends on the specific configuration of the surrogatemodeling workflow and the science itself, and prior work leaves it up to the scientist to find a configuration that delivers the required accuracy for their science problem. Unfortunately, due to the underlying system dynamics, it is rare that a single surrogate configuration presents an optimal accuracy/latency trade-off for the entire simulation. In practice, scientists must choose conservative configurations so that accuracy is always acceptable, forgoing possible acceleration. As an alternative, we propose Proxima, a systematic and automated method for dynamically tuning a surrogatemodeling configuration in response to real-time feedback from the ongoing simulation. Proxima estimates the uncertainty of applying a surrogate approximation in each step of an iterative simulation. Using this information, the specific surrogate configuration can be adjusted dynamically to ensure maximum speedup while sustaining a required accuracy metric. We evaluate Proxima using a Monte Carlo sampling application and find that Proxima respects a wide range of user-defined accuracy goals while achieving speedups of 1.02-5.5× relative to a standard implementation with no surrogate.

High Throughput Training of Deep Surrogates from Large Ensemble Runs

“…The basic workflow sequences two steps: 1) surrogate training, 2) surrogate inference for addressing the target problem, potentially combined with some simulation runs when higher precision is needed. But some are pushing the logic one step further fusing these two steps into a single adaptive ensemble run where a steering logic, relying on shallow or deep learning, tries to improve the global workflow efficiency [9,83,88]. In this paper we focus on the deep surrogate training process (step 1), but our approach has all the necessary flexibility to be used in the fused workflow.…”