暂无分享,去创建一个
Colin Wei | Tengyu Ma | Yining Chen | Colin Wei | Tengyu Ma | Yining Chen
[1] Surya Ganguli,et al. RNNs Can Generate Bounded Hierarchical Languages with Optimal Memory , 2020, EMNLP.
[2] Ding-Xuan Zhou,et al. Universality of Deep Convolutional Neural Networks , 2018, Applied and Computational Harmonic Analysis.
[3] Pablo Barceló,et al. On the Turing Completeness of Modern Neural Network Architectures , 2019, ICLR.
[4] Stefanie Jegelka,et al. ResNet with one-neuron hidden layers is a Universal Approximator , 2018, NeurIPS.
[5] Xiao Wang,et al. Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem , 2019, ICLR.
[6] Andreas Maletti,et al. Recurrent Neural Networks as Weighted Language Recognizers , 2017, NAACL.
[7] Andrea Montanari,et al. A mean field view of the landscape of two-layer neural networks , 2018, Proceedings of the National Academy of Sciences.
[8] Nadav Cohen,et al. On the Expressive Power of Deep Learning: A Tensor Analysis , 2015, COLT 2016.
[9] Navin Goyal,et al. On the Computational Power of Transformers and Its Implications in Sequence Modeling , 2020, CONLL.
[10] Tengyu Ma,et al. Identity Matters in Deep Learning , 2016, ICLR.
[11] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.
[12] Ah Chung Tsoi,et al. Computational Capabilities of Graph Neural Networks , 2009, IEEE Transactions on Neural Networks.
[13] Alon Itai,et al. Learnability with Respect to Fixed Distributions , 1991, Theor. Comput. Sci..
[14] Matthias Hein,et al. Optimization Landscape and Expressivity of Deep CNNs , 2017, ICML.
[15] Ohad Shamir,et al. Size-Independent Sample Complexity of Neural Networks , 2017, COLT.
[16] Eran Yahav,et al. On the Practical Computational Power of Finite Precision RNNs for Language Recognition , 2018, ACL.
[17] Tengyu Ma,et al. On the Ability of Neural Nets to Express Distributions , 2017, COLT.
[18] Abbas Mehrabian,et al. Nearly-tight VC-dimension bounds for piecewise linear neural networks , 2017, COLT.
[19] Lei Wu,et al. Approximation Analysis of Convolutional Neural Networks , 2023, East Asian Journal on Applied Mathematics.
[20] Gilad Yehudai,et al. The Connection Between Approximation, Depth Separation and Learnability in Neural Networks , 2021, COLT.
[21] Yoshua Bengio,et al. On the Expressive Power of Deep Architectures , 2011, ALT.
[22] Raman Arora,et al. Understanding Deep Neural Networks with Rectified Linear Units , 2016, Electron. Colloquium Comput. Complex..
[23] Ohad Shamir,et al. Neural Networks with Small Weights and Depth-Separation Barriers , 2020, Electron. Colloquium Comput. Complex..
[24] Allan Pinkus,et al. Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.
[25] Matus Telgarsky,et al. Neural tangent kernels, transportation mappings, and universal approximation , 2020, ICLR.
[26] Noga Alon,et al. The space complexity of approximating the frequency moments , 1996, STOC '96.
[27] John E. Savage,et al. Models of computation - exploring the power of computing , 1998 .
[28] Dmitry Yarotsky,et al. Universal Approximations of Invariant Maps by Neural Networks , 2018, Constructive Approximation.
[29] Andrew R. Barron,et al. Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.
[30] Samuel A. Korsky,et al. On the Computational Power of RNNs , 2019, ArXiv.
[31] Ohad Shamir,et al. The Power of Depth for Feedforward Neural Networks , 2015, COLT.
[32] Lukasz Kaiser,et al. Attention is All you Need , 2017, NIPS.
[33] David A. McAllester,et al. A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks , 2017, ICLR.
[34] Roman Vershynin,et al. Memory capacity of neural networks with threshold and ReLU activations , 2020, ArXiv.
[35] Colin Wei,et al. Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation , 2019, NeurIPS.
[36] Suvrit Sra,et al. Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity , 2018, NeurIPS.
[37] Ankit Singh Rawat,et al. Are Transformers universal approximators of sequence-to-sequence functions? , 2020, ICLR.
[38] Colin Wei,et al. Improved Sample Complexities for Deep Networks and Robust Classification via an All-Layer Margin , 2019, ICLR.
[39] Amit Daniely,et al. Depth Separation for Neural Networks , 2017, COLT.
[40] Hans-Georg Zimmermann,et al. Recurrent Neural Networks Are Universal Approximators , 2006, ICANN.
[41] Peter L. Bartlett,et al. Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks , 2017, J. Mach. Learn. Res..
[42] Eitan M. Gurari,et al. Introduction to the theory of computation , 1989 .
[43] J. Zico Kolter,et al. Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience , 2019, ICLR.
[44] Amnon Shashua,et al. Convolutional Rectifier Networks as Generalized Tensor Decompositions , 2016, ICML.
[45] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..
[46] Hava T. Siegelmann,et al. On the Computational Power of Neural Nets , 1995, J. Comput. Syst. Sci..
[47] Takeshi Teshima,et al. Universal Approximation Property of Neural Ordinary Differential Equations , 2020, ArXiv.
[48] Jinwoo Shin,et al. Provable Memorization via Deep Neural Networks using Sub-linear Parameters , 2020, COLT.
[49] Akiyoshi Sannai,et al. Universal approximations of permutation invariant/equivariant functions by deep neural networks , 2019, ArXiv.
[50] Matus Telgarsky,et al. Spectrally-normalized margin bounds for neural networks , 2017, NIPS.
[51] Samy Bengio,et al. Understanding deep learning requires rethinking generalization , 2016, ICLR.
[52] Eduardo D. Sontag,et al. Vapnik-Chervonenkis Dimension of Recurrent Neural Networks , 1997, Discret. Appl. Math..
[53] Jooyoung Park,et al. Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.
[54] Ryota Tomioka,et al. Norm-Based Capacity Control in Neural Networks , 2015, COLT.