generated from google/docsy-example
/
refs.bib
338 lines (321 loc) · 14.6 KB
/
refs.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
@InProceedings{doe-abstract,
title = {Surrogate Benchmark Initiative SBI: FAIR Surrogate
Benchmarks Supporting AI and Simulation Research},
author = {Geoffrey Fox and Pete Beckman and Shantenu Jha and
Piotr Luszczek and Vikram Jadhao},
url =
{https://github.com/sbi-fair/sbi-fair.github.io/raw/main/pub/doe_abstract.pdf},
month = feb,
year = 2024,
booktitle = {ASCR Computer Science (CS) Principal Investigators
(PI) Meeting},
pages = 1,
address = {Atlanta, GA},
organization = {U.S. Department of Energy (DOE), Office of Science
(SC)},
overleaf =
{https://www.overleaf.com/project/65b7e7262188975739dae845}
}
@misc{zhong2023rinas,
title = {RINAS: Training with Dataset Shuffling Can Be
General and Fast},
author = {Tianle Zhong and Jiechen Zhao and Xindi Guo and
Qiang Su and Geoffrey Fox},
year = 2023,
eprint = {2312.02368},
archivePrefix ={arXiv},
primaryClass = {cs.DB}
}
@misc{luo2023rtp,
title = {RTP: Rethinking Tensor Parallelism with Memory
Deduplication},
author = {Cheng Luo and Tianle Zhong and Geoffrey Fox},
year = 2023,
eprint = {2311.01635},
archivePrefix ={arXiv},
primaryClass = {cs.DC}
}
@InProceedings{quadri,
author = {},
title = {Quadri-partite Quantum-Assisted VAE as a calorimeter
surrogate},
booktitle = {Bulletin of the American Physical Society},
series = {APS March Meeting},
publisher = {American Physical Society Sites},
url =
{https://meetings.aps.org/Meeting/MAR24/Session/Y50.5}
}
@misc{toledomarín2021deep,
title = {Deep learning approaches to surrogates for solving
the diffusion equation for mechanistic real-world
simulations},
author = {J. Quetzalcóatl Toledo-Marín and Geoffrey Fox and
James P. Sluka and James A. Glazier},
year = 2021,
eprint = {2102.05527},
archivePrefix ={arXiv},
primaryClass = {cond-mat.soft}
}
@ARTICLE{10.3389/fphys.2021.667828,
AUTHOR = {Toledo-Marín, J. Quetzalcóatl and Fox, Geoffrey and
Sluka, James P. and Glazier, James A.},
TITLE = {Deep Learning Approaches to Surrogates for Solving
the Diffusion Equation for Mechanistic Real-World
Simulations},
JOURNAL = {Frontiers in Physiology},
VOLUME = 12,
YEAR = 2021,
URL =
{https://www.frontiersin.org/articles/10.3389/fphys.2021.667828},
DOI = {10.3389/fphys.2021.667828},
ISSN = {1664-042X},
ABSTRACT = {In many mechanistic medical, biological, physical,
and engineered spatiotemporal dynamic models the
numerical solution of partial differential equations
(PDEs), especially for diffusion, fluid flow and
mechanical relaxation, can make simulations
impractically slow. Biological models of tissues and
organs often require the simultaneous calculation of
the spatial variation of concentration of dozens of
diffusing chemical species. One clinical example
where rapid calculation of a diffusing field is of
use is the estimation of oxygen gradients in the
retina, based on imaging of the retinal vasculature,
to guide surgical interventions in diabetic
retinopathy. Furthermore, the ability to predict
blood perfusion and oxygenation may one day guide
clinical interventions in diverse settings, i.e.,
from stent placement in treating heart disease to
BOLD fMRI interpretation in evaluating cognitive
function (Xie et al., <xref ref-type="bibr"
rid="B40">2019</xref>; Lee et al., <xref
ref-type="bibr" rid="B23">2020</xref>). Since the
quasi-steady-state solutions required for
fast-diffusing chemical species like oxygen are
particularly computationally costly, we consider the
use of a neural network to provide an approximate
solution to the steady-state diffusion
equation. Machine learning surrogates, neural
networks trained to provide approximate solutions to
such complicated numerical problems, can often
provide speed-ups of several orders of magnitude
compared to direct calculation. Surrogates of PDEs
could enable use of larger and more detailed models
than are possible with direct calculation and can
make including such simulations in real-time or
near-real time workflows practical. Creating a
surrogate requires running the direct calculation
tens of thousands of times to generate training data
and then training the neural network, both of which
are computationally expensive. Often the practical
applications of such models require thousands to
millions of replica simulations, for example for
parameter identification and uncertainty
quantification, each of which gains speed from
surrogate use and rapidly recovers the up-front
costs of surrogate generation. We use a
Convolutional Neural Network to approximate the
stationary solution to the diffusion equation in the
case of two equal-diameter, circular, constant-value
sources located at random positions in a
two-dimensional square domain with absorbing
boundary conditions. Such a configuration
caricatures the chemical concentration field of a
fast-diffusing species like oxygen in a tissue with
two parallel blood vessels in a cross section
perpendicular to the two blood vessels. To improve
convergence during training, we apply a training
approach that uses roll-back to reject stochastic
changes to the network that increase the loss
function. The trained neural network approximation
is about 1000 times faster than the direct
calculation for individual replicas. Because
different applications will have different criteria
for acceptable approximation accuracy, we discuss a
variety of loss functions and accuracy estimators
that can help select the best network for a
particular application. We briefly discuss some of
the issues we encountered with overfitting,
mismapping of the field values and the geometrical
conditions that lead to large absolute and relative
errors in the approximate solution.}
}
@article{kadupitiya2020machine,
title = {Machine learning surrogates for molecular dynamics
simulations of soft materials},
author = {Kadupitiya, JCS and Sun, Fanbo and Fox, Geoffrey and
Jadhao, Vikram},
journal = {Journal of Computational Science},
volume = 42,
pages = 101107,
year = 2020,
publisher = {Elsevier},
url = {https://par.nsf.gov/servlets/purl/10188151}
}
@inproceedings{jadhao2020integrating,
title = {Integrating machine learning with hpc-driven
simulations for enhanced student learning},
author = {Jadhao, Vikram and Kadupitiya, JCS},
booktitle = {2020 IEEE/ACM Workshop on Education for
High-Performance Computing (EduHPC)},
pages = {25--34},
year = 2020,
organization = {IEEE},
url = {https://api.semanticscholar.org/CorpusID:221376417}
}
@misc{clyde2021proteinligand,
title = {Protein-Ligand Docking Surrogate Models: A
SARS-CoV-2 Benchmark for Deep Learning Accelerated
Virtual Screening},
author = {Austin Clyde and Thomas Brettin and Alexander Partin
and Hyunseung Yoo and Yadu Babuji and Ben Blaiszik
and Andre Merzky and Matteo Turilli and Shantenu Jha
and Arvind Ramanathan and Rick Stevens},
year = 2021,
eprint = {2106.07036},
archivePrefix ={arXiv},
primaryClass = {q-bio.BM},
url = {https://arxiv.org/abs/2106.07036}
}
@article{huerta,
author = {Huerta, E. A. and Blaiszik, Ben and Brinson,
L. Catherine and Bouchard, Kristofer E. and Diaz,
Daniel and Doglioni, Caterina and Duarte, Javier
M. and Emani, Murali and Foster, Ian and Fox,
Geoffrey and Harris, Philip and Heinrich, Lukas and
Jha, Shantenu and Katz, Daniel S. and Kindratenko,
Volodymyr and Kirkpatrick, Christine R. and
Lassila-Perini, Kati and Madduri, Ravi K. and
Neubauer, Mark S. and Psomopoulos, Fotis E. and Roy,
Avik and R{\"u}bel, Oliver and Zhao, Zhizhen and
Zhu, Ruike},
journal = {Scientific Data},
number = 1,
pages = 487,
title = {FAIR for AI: An interdisciplinary and international
community building perspective},
volume = 10,
year = 2023,
url = {https://doi.org/10.1038/s41597-023-02298-6}
}
@misc{vonlaszewski2022hybrid,
title = {Hybrid Reusable Computational Analytics Workflow
Management with Cloudmesh},
author = {von Laszewski, Gregor and J. P. Fleischer and
Geoffrey C. Fox},
year = 2022,
eprint = {2210.16941},
archivePrefix ={arXiv},
primaryClass = {cs.DC}
}
@misc{chennamsetti2023mlcommons,
title = {MLCommons Cloud Masking Benchmark with Early
Stopping},
author = {Varshitha Chennamsetti and von Laszewski, Gregor and
Ruochen Gu and Laiba Mehnaz and Juri Papay and
Samuel Jackson and Jeyan Thiyagalingam and Sergey
V. Samsonau and Geoffrey C. Fox},
year = 2023,
eprint = {2401.08636},
archivePrefix ={arXiv},
primaryClass = {cs.DC}
}
@misc{vonlaszewski2023overview,
title = {An Overview of MLCommons Cloud Mask Benchmark:
Related Research and Data},
author = {von Laszewski, Gregor and Ruochen Gu},
year = 2023,
eprint = {2312.04799},
archivePrefix ={arXiv},
primaryClass = {cs.DC}
}
@misc{vonlaszewski2023whitepaper,
title = {Whitepaper on Reusable Hybrid and Multi-Cloud
Analytics Service Framework},
author = {von Laszewski, Gregor and Wo Chang and Russell
Reinsch and Olivera Kotevska and Ali Karimi and
Abdul Rahman Sattar and Garry Mazzaferro and
Geoffrey C. Fox},
year = 2023,
eprint = {2310.17013},
archivePrefix ={arXiv},
primaryClass = {cs.DC}
}
@inproceedings{las-2023-escience,
address = {Limassol, Cyprus},
author = {von Laszewski, Gregor and Fleischer, J.P. and Fox,
Geoffrey C. and Juri Papay and Sam Jackson and Jeyan
Thiyagalingam},
booktitle = {eScience'23},
month = {October},
organization = {Second Workshop on Reproducible Workflows, Data, and
Security (ReWorDS 2022)},
title = {Templated Hybrid Reusable Computational Analytics
Workflow Management with Cloudmesh, Applied to the
Deep Learning MLCommons Cloudmask Application},
url =
{https://github.com/cyberaide/paper-cloudmesh-cc-ieee-5-pages/raw/main/vonLaszewski-cloudmesh-cc.pdf},
year = 2023
}
@article{las-2023-mlcommons-edu-eq,
author = {von Laszewski, Gregor and Fleischer, J.P. and
Knuuti, R. and Fox, G.C. and Kolessar, J. and
Butler, T.S. and Fox, J.},
journal = {Frontiers in High Performance Computing,},
month = {October},
number = 1233877,
pages = 31,
title = {Opportunities for enhancing MLCommons efforts while
leveraging insights from educational MLCommons
earthquake benchmarks efforts},
url = {https://doi.org/10.3389/fhpcp.2023.1233877},
volume = 1,
year = 2023
}
@misc{www-clodmesh-repos,
author = {von Laszewski, Gregor},
title = {Cloudmesh},
howpublished = {Web Page},
url = {https://github.com/orgs/cloudmesh/repositories},
month = jan,
year = 2024
}
@inproceedings{las-2022-icbicc,
address = {Chengdu, China},
annote = {Over the last several years, the computation
landscape for conducting data analytics has
completely changed. While in the past, a lot of the
activities have been undertaken in isolation by
companies, and research institutions, today's
infrastructure constitutes a wealth of analytics
services offered by a variety of providers that
offer opportunities for reuse, interactions while
leveraging service collaboration, and service
cooperation. In this talk, we project our vision to
develop an analytics services framework to integrate
reusable hybrid multi-services across different
cloud infrastructure and service providers as well
as on-premise infrastructure and services. It
includes (a) analytics services that explicitly
target the intersection of hybrid multi-provider
analytics services, (b) the integration of sensor
networks into the service data, (c) the integration
of advanced modelling services as part of analytical
tasks such as earthquake prediction, and (d) the
coordination of these services. We showcase how our
vision can integrate leveraging service composition
with cooperation and competition analytics
services. We demonstrate the activities while
utilizing benchmark analytics services as used by
the MLCommons science benchmark working group.},
author = {von Laszewski, Gregor},
booktitle = {4th International Conference on Big data, IoT, and
Cloud Computing (ICBICC 2022)},
month = {December},
note = {Keynote},
publisher = {IASED},
title = {Reusable Hybrid and Multi-Cloud Analytics Service
Framework},
url = {www.icbicc.org},
year = 2022
}