28. 1. Mandelbrot, B. B. The variation of certain speculative prices.
2. Edgar E. Peters. Fractal market analysis: applying chaos theory to investment and economics.
3. Guangxi Cao, Jie Cao, Longbing Xu. Asymmetric multifractal scaling behavior in the Chinese stock market: Based on
asymmetric MF-DFA.
4. Walid Mensi, Atef Hamdi, Syed Jawad Hussain Shahzad, Muhammad Shafiullah, Khamis Hamed Al-Yahyaee. Modeling cross-
correlations and efficiency of Islamic and conventional banks from Saudi Arabia: Evidence from MF-DFA and MF-DXA
approaches.
5. Minhyuk Lee, Jae Wook Song, Sondo Kim and Woojin Chang. Asymmetric market efficiency using the index-based
asymmetric-MFDFA.
6. Neyshabur, B., Tomioka, R. and Srebro, N. Norm-based capacity control in neural networks.
7. Bartlett, P. L., Foster, D. J. and Telgarsky, M. J. Spectrally-normalized margin bounds for neural networks.
8. Golowich, N., Rakhlin, A. and Shamir, O. Size-independent sample complexity of neural networks.
9. Hardt, M., Recht, B. and Singer, Y. Train faster, generalize better: Stability of stochastic gradient descent.
10. Keskar, N. S., Nocedal, J., Tang, P. T. P., Mudigere, D. and Smelyanskiy, M. On large-batch training for deep learning:
Generalization gap and sharp minima.
11. Belkin, M., Hsu, D., Ma, S. and Mandal, S. Reconciling modern machine-learning practice and the classical bias–variance
trade-off.
参考文献
28
帰納バイアスが成立する条件
29. 12. Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B. and Sutskever, I. Deep double descent: Where bigger models and
more data hurt.
13. Hastie, T., Montanari, A., Rosset, S. and Tibshirani, R. J. Surprises in high-dimensional ridgeless least squares interpolation.
14. Saxe, A. M., McClelland, J. L., and Ganguli, S. Exact solutions to the nonlinear dynamics of learning in deep linear neural
networks.
15. Pennington, J., Schoenholz, S., and Ganguli, S. Resurrecting the sigmoid in deep learning through dynamical isometry: theory
and practice.
16. Pennington, J., Schoenholz, S. S., and Ganguli, S. The emergence of spectral universality in deep networks.
17. Xiao, L., Bahri, Y., Sohl-Dickstein, J., Schoenholz, S. S., and Pennington, J. Dynamical Isometry and a Mean Field Theory of
CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks.
18. Anthony, M. and Bartlett, P. L. Neural Network Learning : Theoretical Foundations
19. Tan, M. and Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks.
20. Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein. Visualizing the Loss Landscape of Neural Nets.
21. Wojciech Tarnowski, Piotr Warchoł, Stanisław Jastrzębski, Jacek Tabor, Maciej A. Nowak. Dynamical Isometry is Achieved in
Residual Networks in a Universal Way for any Activation Function.
22. J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation.
23. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition.
参考文献
29
帰納バイアスが成立する条件
30. 24. C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going
Deeper with Convolutions.
25. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia
Polosukhin. Attention is all you need.
26. Ilya Sutskever, Oriol Vinyals, Quoc V. Le. Sequence to Sequence Learning with Neural Networks.
27. li Deng, Geoffrey Hinton, and Brian Kingsbury. New types of deep neural network learning for speech recognition and related
applications.
28. A. Mohamed, G.E. Dahl, and G. Hinton. Acoustic Modeling Using Deep Belief Networks.
29. Jonathan Frankle and Michael Carbin. The lottery ticket hypothesis: Finding sparse, trainable neural networks.
30. Vaishnavh Nagarajan and J Zico Kolter. Uniform convergence may be unable to explain generalization in deep learning.
31. Gintare Karolina Dziugaite and Daniel M Roy. Computing nonvacuous generalization bounds for deep (stochastic) neural
networks with many more parameters than training data.
32. Kenji Kawaguchi, Leslie Pack Kaelbling, and Yoshua Bengio. Generalization in deep learning.
33. Behnam Neyshabur, Ryota Tomioka, and Nathan Srebro. In search of the real inductive bias: On the role of implicit
regularization in deep learning.
34. Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin, and James Stokes. Fisher-rao metric, geometry, and complexity of
neural networks.
参考文献
30
帰納バイアスが成立する条件
31. 35. Behnam Neyshabur, Srinadh Bhojanapalli, and Nathan Srebro. A PAC-Bayesian approach to Spectrally-Normalized margin
bounds for neural networks.
36. Sanjeev Arora, Rong Ge, Behnam Neyshabur, and Yi Zhang. Stronger generalization bounds for deep nets via a compression
approach.
37. Wenda Zhou, Victor Veitch, Morgane Austern, Ryan P Adams, and Peter Orbanz. Non-vacuous generalization bounds at the
ImageNet scale: a PAC-Bayesian compression approach.
38. Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires
rethinking generalization.
39. Krizhevsky, A., Sutskever, I., and Hinton, G. E. ImageNet Classification with Deep Convolutional Neural Networks.
40. Simonyan, K. and Zisserman, A. Very Deep Convolutional Networks for Large-Scale Image Recognition.
41. He, K., Zhang, X., Ren, S., and Sun, J. Deep Residual Learning for Image Recognition.
42. Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger. Densely Connected Convolutional Networks.
43. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav
Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel HerbertVoss, Gretchen Krueger, Tom Henighan, Rewon Child,
Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray,
Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020.
Language Models are Few-Shot Learners.
参考文献
31
帰納バイアスが成立する条件
32. 44. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and
Veselin Stoyanov. RoBERTa: A Robustly Optimized BERT Pretraining Approach.
45. Guido Montúfar, Razvan Pascanu, Kyunghyun Cho, Yoshua Bengio. On the Number of Linear Regions of Deep Neural
Networks.
46. Huan Xiong, Lei Huang, Mengyang Yu, Li Liu, Fan Zhu, Ling Shao. On the Number of Linear Regions of Convolutional Neural
Networks.
47. Xiao Zhang & Dongrui Wu. Empirical Studies on the Properties of Linear Regions in Deep Neural Networks.
48. Razvan Pascanu, Tomas Mikolov, Yoshua Bengio On the difficulty of training Recurrent Neural Networks.
49. Yoshua Bengio, Patrice Simard, Paolo Frasconi. Learning long-term dependencies with gradient descent is difficult.
50. Sepp Hochreiter. The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions.
51. Y. Bengio. Learning Deep Architectures for AI.
52. X. Glorot and Y. Bengio. Understanding the difficulty of training deep feedforward neural networks.
53. D. Erhan, Y. Bengio, A. Courville, P.A. Manzagol, and P. Vincent. Why Does Unsupervised Pre-training Help Deep Learning?.
54. Y.N. Dauphin and Y. Bengio. Big Neural Networks Waste Capacity.
55. Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires
rethinking generalization.
参考文献
32
帰納バイアスが成立する条件
33. 56. P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A.
Santoro, R. Faulkner, C. Gulcehre, F. Song, A. Ballard, J. Gilmer, G. Dahl, A. Vaswani, K. Allen, C. Nash, V. Langston, C.
Dyer, N. Heess, D. Wierstra, P. Kohli, M. Botvinick, O. Vinyals, Y. Li, and R. Pascanu. Relational inductive biases, deep
learning, and graph networks.
57. Daniel Soudry, Elad Ho er, Mor Shpigel Nacson, Suriya Gunasekar, and Nathan Srebro. The Implicit Bias of Gradient
Descent on Separable Data.
58. Vatsal Shah, Anastasios Kyrillidis, and Sujay Sanghavi. Minimum norm solutions do not always generalize well for over-
parameterized problems.
59. Sanjeev Arora, Nadav Cohen, Wei Hu, and Yuping Luo. Implicit Regularization in Deep Matrix Factorization.
60. Depen Morwani & Harish G. Ramaswamy. Inductive Bias of Gradient Descent for Exponentially Weight Normalized Smooth
Homogeneous Neural Nets.
61. Sanjeev Arora, Nadav Cohen, Noah Golowich, Wei Hu. A Convergence Analysis of Gradient Descent for Deep Linear Neural
Networks.
62. Avrim Blum and Ronald L Rivest. Training a 3-Node Neural Network is NP-Complete.
63. Murty, K. G. and Kabadi, S. N. Some NP-complete problems in quadratic and nonlinear programming.
64. Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, and Oriol Vinyals. Understanding deep learning requires
rethinking generalization.
参考文献
33
帰納バイアスが成立する条件
34. 65. Grzegorz Swirszcz, Wojciech Marian Czarnecki, and Razvan Pascanu. Local minima in training of deep networks.
66. Mor Shpigel Nacson, Jason Lee, Suriya Gunasekar, Pedro Henrique Pamplona Savarese, Nathan Srebro, and Daniel Soudry.
Convergence of Gradient Descent on Separable Data.
67. Mor Shpigel Nacson, Nathan Srebro, and Daniel Soudry. Stochastic Gradient Descent on Separable Data: Exact Convergence
with a Fixed Learning Rate.
68. Suriya Gunasekar, Jason Lee, Daniel Soudry, and Nathan Srebro. Characterizing Implicit Bias in Terms of Optimization
Geometry.
69. Ziwei Ji and Matus Telgarsky. A refined primal-dual analysis of the implicit bias.
70. Ziwei Ji and Matus Telgarsky. The implicit bias of gradient descent on nonseparable data.
71. Ziwei Ji and Matus Telgarsky. Gradient descent aligns the layers of deep linear networks.
72. Suriya Gunasekar, Jason D Lee, Daniel Soudry, and Nati Srebro. Implicit Bias of Gradient Descent on Linear Convolutional
Networks.
73. Mor Shpigel Nacson, Suriya Gunasekar, Jason Lee, Nathan Srebro, and Daniel Soudry. Lexicographic and Depth-Sensitive
Margins in Homogeneous and Non-Homogeneous Deep Models.
74. Lénaïc Chizat, Francis Bach. Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic
Loss.
75. Kaifeng Lyu and Jian Li. Gradient Descent Maximizes the Margin of Homogeneous Neural Networks.
参考文献
34
帰納バイアスが成立する条件
35. 76. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander CBerg. SSD:
Single Shot Multibox Detector.
77. Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You Only Look Once: Unified, Real-time Object Detection.
78. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster R-CNN: Towards Real-time Object Detection with Region
Proposal Networks.
79. Kaiming He, Georgia Gkioxari, Piotr Doll ar, and Ross Girshick. Mask R-CNN.
80. Alexander Kirillov, Kaiming He, Ross Girshick, Carsten Rother, and Piotr Dollar. Panoptic Segmentation.
81. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation.
82. Jonathan L Long, Ning Zhang, and Trevor Darrell. Do Convnets Learn Correspondence?
83. Xufeng Han, Thomas Leung, Yangqing Jia, Rahul Sukthankar, and Alexander C Berg. MatchNet: Unifying Feature and Metric
Learning for Patch-Based Matching.
84. Sergey Zagoruyko and Nikos Komodakis. Learning to Compare Image Patches via Convolutional Neural Networks.
85. Joao Carreira and Andrew Zisserman. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset.
86. Kensho Hara, Hirokatsu Kataoka, and Yutaka Satoh. Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and
ImageNet?.
87. Karen Simonyan and Andrew Zisserman. Two-Stream Convolutional Networks for Action Recognition in Videos.
88. Leon A Gatys, Alexander S Ecker, and Matthias Bethge. Image Style Transfer Using Convolutional Neural Networks.
参考文献
35
帰納バイアスが成立する条件
36. 88. Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua
Bengio. Generative Adversarial Networks.
89. Durk P Kingma and Prafulla Dhariwal. Glow: Generative Flow with Invertible 1x1 Convolutions.
90. Ossama Abdel-Hamid, Abdel-rahman Mohamed, Hui Jiang, Li Deng, Gerald Penn, Dong Yu. Convolutional Neural Networks
for Speech Recognition.
91. Yann LeCun, Yoshua Bengio, et al. Convolutional networks for images, speech, and time series.
92. Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew
Senior, and Koray Kavukcuoglu. WaveNet: A Generative Model for Raw Audio.
93. Keunwoo Choi, Gy orgy Fazekas, Mark Sandler, and Kyunghyun Cho. Convolutional recurrent neural networks for music
classification.
94. Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis, Jort F. Gemmeke, Aren Jansen, R. Channing Moore, Manoj Plakal,
Devin Platt, Rif A. Saurous, Bryan Seybold, Malcolm Slaney, Ron J. Weiss, Kevin Wilson. CNN Architectures for Large-Scale
Audio Classification.
95. Stanley J Reeves. Fast image restoration without boundary artifacts.
96. Kyunghyun Cho, Bart van Merri enboer, Dzmitry Bahdanau, and Yoshua Bengio. On the Properties of Neural Machine
Translation: Encoder-Decoder Approaches.
97. Cicero Dos Santos and Maira Gatti. Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts.
参考文献
36
帰納バイアスが成立する条件
37. 98. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation.
99. Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann Lecun. Spectral Networks and Locally Connected Networks on
Graphs.
100.David K Duvenaud, Dougal Maclaurin, Jorge Iparraguirre, Rafael Bombarell, Timothy Hirzel, Al an Aspuru-Guzik, Ryan P
Adams. Convolutional Networks on Graphs for Learning Molecular Fingerprints.
101.Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, Max Welling. Modeling Relational Data
with Graph Convolutional Networks.
102.Anadi Chaman, Ivan Dokmanić. Truly shift-invariant convolutional neural networks
103.David A. McAllester. Some PAC-Bayesian Theorems.
104.David A. McAllester. PAC-Bayesian Model Averaging.
105.Behnam Neyshabur, Srinadh Bhojanapalli, David McAllester, and Nati Srebro. Exploring Generalization in Deep Learning.
106.Behnam Neyshabur, Srinadh Bhojanapalli, and Nathan Srebro. A PAC-Bayesian Approach to Spectrally-Normalized Margin
Bounds for Neural Networks.
107.Jiang, Y., Neyshabur, B., Krishnan, D., Mobahi, H., and Bengio, S. Fantastic Generalization Measures and Where to Find
Them.
108.Guillermo Valle-Pérez, Ard A. Louis. Generalization bounds for deep learning.
109.Tsung-Han Hsieh, Li Su, Yi-Hsuan Yang. A Streamlined Encoder/Decoder Architecture for Melody Extraction.
参考文献
37
帰納バイアスが成立する条件
38. 109.Ta-Wei Tang, Wei-Han Kuo, Jauh-Hsiang Lan, Chien-Fang Ding, Hakiem Hsu, Hong-Tsu Young. Anomaly Detection Neural
Network with Dual Auto-Encoders GAN and Its Industrial Inspection Applications.
110.Yan Hong, Li Niu, Jianfu Zhang, Weijie Zhao, Chen Fu, Liqing Zhang. F2GAN: Fusing-and-Filling GAN for Few-shot Image
Generation.
111.Vasiliy Kuzmin, Fyodor Kravchenko, Artem Sokolov, Jie Geng. Real-time Streaming Wave-U-Net with Temporal Convolutions
for Multichannel Speech Enhancement.
112.Yihe Dong, Jean-Baptiste Cordonnier, Andreas Loukas. Attention is not all you need: pure attention loses rank doubly
exponentially with depth.
113.Vaishnavh Nagarajan, J. Zico Kolter. Nagarajan, V. and Kolter, J. Z. Uniform convergence may be unable to explain
generalization in deep learning.
114.Ohad Shamir. Are ResNets Provably Better than Linear Predictors?
参考文献
38
帰納バイアスが成立する条件