-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathpaper.bib
More file actions
424 lines (372 loc) · 12.8 KB
/
Copy pathpaper.bib
File metadata and controls
424 lines (372 loc) · 12.8 KB
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
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
@inproceedings{kingma2015adam,
title={Adam: A method for stochastic optimization},
author={Kingma, Diederik P. and Ba, Jimmy},
booktitle={International Conference on Learning Representations (ICLR)},
year={2015}
}
@manual{octave,
title = {{GNU Octave} version 4.4.0 manual: a high-level interactive
language for numerical computations},
author = {John W. Eaton and David Bateman and S{\o}ren Hauberg and Rik
Wehbring},
year = {2018},
url = {https://www.gnu.org/software/octave/doc/v4.4.1/},
}
@article{zhu1997algorithm,
title={Algorithm 778: {L-BFGS-B}: Fortran subroutines for large-scale
bound-constrained optimization},
author={Zhu, Ciyou and Byrd, Richard H and Lu, Peihuang and Nocedal, Jorge},
journal={ACM Transactions on Mathematical Software (TOMS)},
volume={23},
number={4},
pages={550--560},
year={1997},
publisher={ACM}
}
@article{mlpack2018,
title = {mlpack 3: a fast, flexible machine learning library},
author = {Curtin, Ryan R. and Edel, Marcus and Lozhnikov, Mikhail and
Mentekidis, Yannis and Ghaisas, Sumedh and Zhang,
Shangtong},
journal = {Journal of Open Source Software},
volume = {3},
issue = {26},
pages = {726},
year = {2018},
doi = {10.21105/joss.00726},
url = {https://doi.org/10.21105/joss.00726}
}
@article{RevelsLubinPapamarkou2016,
title = {Forward-Mode Automatic Differentiation in {Julia}},
author = {{Revels}, J. and {Lubin}, M. and {Papamarkou}, T.},
journal = {arXiv:1607.07892},
year = {2016},
url = {https://arxiv.org/abs/1607.07892}
}
@article{kirkpatrick1983optimization,
title={Optimization by Simulated Annealing},
author={Scott Kirkpatrick and C.D. Gelatt and Mario P. Vecchi},
journal={Science},
volume={220},
number={4598},
pages={671--680},
year={1983},
publisher={American Association for the Advancement of Science}
}
@article{paszke2017automatic,
title={Automatic differentiation in {PyTorch}},
author={Paszke, Adam and Gross, Sam and Chintala, Soumith and Chanan, Gregory
and Yang, Edward and DeVito, Zachary and Lin, Zeming and Desmaison, Alban and
Antiga, Luca and Lerer, Adam},
journal={Autodiff Workshop at NIPS},
year={2017}
}
@article{cox1958regression,
title={The regression analysis of binary sequences},
author={Cox, David R},
journal={Journal of the Royal Statistical Society. Series B (Methodological)},
pages={215--242},
year={1958},
publisher={JSTOR}
}
@inproceedings{goldberger2005neighbourhood,
title={Neighbourhood components analysis},
author={Goldberger, Jacob and Hinton, Geoffrey E and Roweis, Sam T and Salakhutdinov, Ruslan R},
booktitle={Advances in neural information processing systems},
pages={513--520},
year={2005}
}
@inproceedings{weinberger2006introduction,
title={An introduction to nonlinear dimensionality reduction by maximum variance unfolding},
author={Weinberger, Kilian Q and Saul, Lawrence K},
booktitle={AAAI},
volume={6},
pages={1683--1686},
year={2006}
}
@article{schmidhuber2015deep,
title={Deep learning in neural networks: An overview},
author={Schmidhuber, J{\"u}rgen},
journal={Neural Networks},
volume={61},
pages={85--117},
year={2015},
publisher={Elsevier}
}
@article{Rosenbrock1960,
title = {An Automatic Method for Finding the Greatest or Least Value of a
Function},
author = {Rosenbrock, Howard H.},
journal = {The Computer Journal},
volume = {3},
pages = {175--184},
year = {1960}
}
@inproceedings{jia2014caffe,
title={Caffe: Convolutional architecture for fast feature embedding},
author={Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
booktitle={ACM International Conference on Multimedia},
pages={675--678},
year={2014},
}
@article{abadi2016tensorflow,
title={Tensorflow: Large-scale machine learning on heterogeneous distributed systems},
author={Abadi, Mart{\'\i}n and Agarwal, Ashish and Barham, Paul and Brevdo, Eugene and Chen, Zhifeng and Citro, Craig and Corrado, Greg S and Davis, Andy and Dean, Jeffrey and others},
journal={arXiv:1603.04467},
year={2016}
}
@article{abadi2016tensorflow_full,
title={Tensorflow: Large-scale machine learning on heterogeneous distributed systems},
author={Abadi, Mart{\'\i}n and Agarwal, Ashish and Barham, Paul and Brevdo, Eugene and Chen, Zhifeng and Citro, Craig and Corrado, Greg S and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and others},
journal={arXiv:1603.04467},
year={2016}
}
@misc{chollet2015,
author = {François Chollet},
title = {Keras},
year = {2015},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/fchollet/keras}},
commit = {f2501c4}
}
@article{sanderson2016armadillo,
title={Armadillo: a template-based {C++} library for linear algebra},
author={Sanderson, Conrad and Curtin, Ryan},
journal={Journal of Open Source Software},
year={2016},
volume={1},
pages={26},
}
@inproceedings{smaragdakis2000mixin,
title={Mixin-based programming in {C++}},
author={Smaragdakis, Yannis and Batory, Don},
booktitle={International Symposium on Generative and Component-Based Software Engineering, Lecture Notes in Computer Science},
volume={2177},
pages={164--178},
year={2000},
organization={Springer}
}
@article{pedregosa2011scikit,
title={Scikit-learn: Machine learning in {Python}},
author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and others},
journal={Journal of Machine Learning Research},
volume={12},
number={Oct},
pages={2825--2830},
year={2011}
}
@article{pedregosa2011scikit_full,
title={Scikit-learn: Machine learning in Python},
author={Pedregosa, Fabian and Varoquaux, Ga{\"e}l and Gramfort, Alexandre and Michel, Vincent and Thirion, Bertrand and Grisel, Olivier and Blondel, Mathieu and Prettenhofer, Peter and Weiss, Ron and Dubourg, Vincent and others},
journal={Journal of Machine Learning Research},
volume={12},
number={Oct},
pages={2825--2830},
year={2011}
}
@article{mogensen2018optim,
author = {Mogensen, Patrick Kofod and Riseth, Asbj{\o}rn Nilsen},
title = {Optim: A mathematical optimization package for {Julia}},
journal = {Journal of Open Source Software},
year = {2018},
volume = {3},
number = {24},
pages = {615},
doi = {10.21105/joss.00615}
}
@misc{jones2014scipy,
title={{SciPy}: open source scientific tools for {Python}},
author={Jones, Eric and Oliphant, Travis and Peterson, Pearu},
year={2014},
note="\url{http://www.scipy.org/}",
}
@article{mlpack2013,
title = {{MLPACK}: A Scalable {C++} Machine Learning Library},
author = {Curtin, Ryan R. and Cline, James R. and Slagle, Neil P. and
March, William B. and Ram, P. and Mehta, Nishant A. and Gray,
Alexander G.},
journal = {Journal of Machine Learning Research},
volume = {14},
pages = {801--805},
year = {2013}
}
@book{Alexandrescu2001,
author = {Alexandrescu, Andrei},
title = {Modern C++ Design: Generic Programming and Design Patterns Applied},
year = {2001},
isbn = {0-201-70431-5},
publisher = {Addison-Wesley Longman Publishing Co., Inc.},
address = {Boston, MA, USA},
}
@article{icopust2017,
title = {Designing and building the mlpack open-source machine learning
library},
author = {Curtin, Ryan R. and Edel, Marcus},
journal={arXiv preprint arXiv:1708.05279},
year={2017}
}
@inproceedings{pasc2017,
title = {Armadillo: C++ template metaprogramming for compile-time optimization
of linear algebra},
author = {Sanderson, Conrad and Curtin, Ryan R.},
booktitle={Platform for Advanced Scientific Computing (PASC) Conference},
year={2017}
}
@book{Vandevoorde2002sfinae,
author = {Vandevoorde, David and Josuttis, Nicolai M.},
edition = {1},
isbn = {9780201734843},
publisher = {Addison-Wesley Professional},
title = {{C++ Templates: The Complete Guide}},
year = {2002}
}
@article{sonnenburg2010shogun,
title={The {SHOGUN} machine learning toolbox},
author={Sonnenburg, S. and R{\"a}tsch, G. and Henschel, S. and Widmer, C. and
Behr, J. and Zien, A. and de Bona, F. and
Binder, A. and Gehl, C. and Franc, V.},
journal={Journal of Machine Learning Research},
volume={11},
pages={1799--1802},
year={2010}
}
@techreport{Langford2007VW,
title={Vowpal wabbit open source project},
author={Langford, J. and L. Li and Strehl, A.},
institution={Yahoo!},
year={2007},
}
@misc{mathworks2017OTB,
author = {Mathworks},
title = {MATLAB Optimization Toolbox},
year = 2017,
note = {The MathWorks, Natick, MA, USA}
}
@misc{nvidia2015,
title={{NVBLAS Library}},
author={{NVIDIA}},
year={2015},
howpublished={\url{http://docs.nvidia.com/cuda/nvblas}}
}
@book{Rosen_2004_full,
title = {Open Source Licensing: Software Freedom and Intellectual Property Law},
author = {Lawrence Rosen},
year = {2004},
publisher = {Prentice Hall}
}
@book{Rosen_2004,
title = {Open Source Licensing},
author = {Lawrence Rosen},
year = {2004},
publisher = {Prentice Hall}
}
@book{Abrahams_2004,
author = {D. Abrahams and A. Gurtovoy},
title = {C++ Template Metaprogramming: Concepts, Tools, and Techniques from Boost and Beyond},
publisher = {Addison-Wesley Professional},
year = {2004}
}
@misc{ucimlrepository,
author = "M. Lichman",
year = "2013",
title = "{UCI} {M}achine {L}earning {R}epository",
note = "\url{http://archive.ics.uci.edu/ml}",
}
@article{Robbins_1951,
author = {Herbert Robbins and Sutton Monro},
title = {A Stochastic Approximation Method},
journal = {Annals of Mathematical Statistics},
volume = {22},
number = {3},
year = {1951},
pages = {400--407}
}
@article{Mokhtari_2018,
author = {Aryan Mokhtari and Mark Eisen and Alejandro Ribeiro},
title = {{IQN}: An Incremental Quasi-Newton Method with Local Superlinear Convergence Rate},
journal = {SIAM Journal on Optimization},
volume = {28},
number = {2},
year = {2018},
pages = {1670--1698}
}
@article{Hestenes_1969,
author = {Magnus R. Hestenes},
title = {Multiplier and gradient methods},
journal = {Journal of Optimization Theory and Applications},
volume = {4},
number = {5},
year = {1969},
pages = {303--320}
}
@inproceedings{lam2015numba,
title={Numba: A {LLVM}-based python {JIT} compiler},
author={Lam, Siu Kwan and Pitrou, Antoine and Seibert, Stanley},
booktitle={Second Workshop on the LLVM Compiler Infrastructure in HPC},
pages={7},
year={2015},
}
@inproceedings{maclaurin2015autograd,
title={Autograd: Effortless gradients in numpy},
author={Maclaurin, Dougal and Duvenaud, David and Adams, Ryan P},
booktitle={AutoML Workshop at ICML},
year={2015}
}
@inproceedings{hogwild_nips_2011,
title = {{HOGWILD!}: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent},
author = {Feng Niu and Benjamin Recht and Christopher R\'{e} and Stephen J. Wright},
booktitle = {Advances in Neural Information Processing Systems},
year = {2011}
}
@article{Hansen_2001,
author = {Nikolaus Hansen and Andreas Ostermeier},
title = {Completely Derandomized Self-Adaptation in Evolution Strategies},
journal = {Evolutionary Computation},
volume = {9},
number = {2},
year = {2001},
pages = {159--195}
}
@misc{Belew_1990,
author = {Richard K. Belew and John McInerney and Nicol N. Schraudolph},
title = {Evolving Networks: Using the Genetic Algorithm with Connectionist Learning},
year = {1990},
note = "CSE Technical Report \#CS90-174, University of California at San Diego",
}
@article{Frank_1956,
author = {Marguerite Frank and Philip Wolfe},
title = {An Algorithm for Quadratic Programming},
journal = {Naval Research Logistics Quarterly},
volume = {3},
number = {1-2},
year = {1956},
pages = {95--110}
}
@article{Duchi_2011,
author = {John Duchi and Elad Hazan and Yoram Singer},
title = {Adaptive Subgradient Methods for Online Learning and Stochastic Optimization},
journal = {Journal of Machine Learning Research},
volume = {12},
pages = {2121--2159},
year = {2011}
}
@article{Zeiler_2012,
author = {Matthew D. Zeiler},
title = {{ADADELTA}: An Adaptive Learning Rate Method},
journal = {arXiv:1212.5701},
year = {2012},
}
@article{Ruder_2016,
author = {Sebastian Ruder},
title = {An overview of gradient descent optimization algorithms},
journal = {arXiv:1609.04747},
year = {2016},
}
@book{Vandevoorde_2018,
title={C++ Templates: The Complete Guide},
author={Vandevoorde, David and Josuttis, Nicolai M},
edition={2nd},
year={2017},
publisher={Addison-Wesley}
}