[Colloquium] Wan/MS Presentation/Sep 27, 2019

[Margaret Jaffey]

This is an announcement of Chengcheng Wan's MS Presentation.

------------------------------------------------------------------------------
Date:  Friday, September 27, 2019

Time:  2:00 PM

Place:  John Crerar Library 298

M.S. Candidate:  Chengcheng Wan

M.S. Paper Title: ALERT: Accurate Anytime Learning for Energy and
Timeliness

Abstract:
An increasing number of software applications incorporate runtime Deep
Neural Network (DNN) inference for its great accuracy in many problem
domains. While much prior work has separately tackled the problems of
improving DNN-inference accuracy and improving DNN-inference
efficiency, an important problem is under-explored: disciplined
methods for dynamically managing application-specific latency,
accuracy, and energy tradeoffs and constraints at run time. To address
this need, we propose ALERT, a co-designed combination of runtime
system and DNN nesting technique. The runtime takes latency, accuracy,
and energy constraints, and uses dynamic feedback to predict the best
DNN-model and system power-limit setting. The DNN nesting creates a
type of flexible network that efficiently delivers a series of results
with increasing accuracy as time goes on. These two parts well
complement each other: the runtime is aware of the tradeoffs of
different DNN settings, and the nested DNNs' flexibility allows the
runtime prediction to satisfy application requirements even in
unpredictable, changing environments. On real systems for both image
and speech, ALERT achieves close-to-optimal results. Comparing with
the optimal static DNN-model and power-limit setting, which is
impractical to predict, ALERT achieves a harmonic mean 33% of energy
savings while satisfying accuracy constraints, and reduces
image-classification error rate by 58% and sentence-prediction
perplexity by 52% while satisfying energy constraints.

Chengcheng's advisor is Prof. Shan Lu

Login to the Computer Science Department website for details:
 https://newtraell.cs.uchicago.edu/phd/ms_announcements#cwan

=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Margaret P. Jaffey            margaret at cs.uchicago.edu
Department of Computer Science
Student Support Rep (Ry 156)               (773) 702-6011
The University of Chicago      http://www.cs.uchicago.edu
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=