KAMA-NNs: Low-dimensional Rotation Based Neural Networks
暂无分享,去创建一个
Krzysztof Choromanski | Jeffrey Pennington | Yunhao Tang | Aldo Pacchiano | Jeffrey Pennington | K. Choromanski | Aldo Pacchiano | Yunhao Tang
[1] M. Kac. Foundations of Kinetic Theory , 1956 .
[2] E. Janvresse. Spectral gap for Kac's model of Boltzmann equation , 2001 .
[3] J. Gallier,et al. COMPUTING EXPONENTIALS OF SKEW-SYMMETRIC MATRICES AND LOGARITHMS OF ORTHOGONAL MATRICES , 2002 .
[4] Bernard Chazelle,et al. Approximate nearest neighbors and the fast Johnson-Lindenstrauss transform , 2006, STOC '06.
[5] Benjamin Recht,et al. Random Features for Large-Scale Kernel Machines , 2007, NIPS.
[6] Jan Vyb'iral. A variant of the Johnson-Lindenstrauss lemma for circulant matrices , 2010, 1002.2847.
[7] Yuval Tassa,et al. MuJoCo: A physics engine for model-based control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.
[8] Hui Zhang,et al. New bounds for circulant Johnson-Lindenstrauss embeddings , 2013, ArXiv.
[9] S. Mischler,et al. Kac’s program in kinetic theory , 2013 .
[10] Gal Chechik,et al. Coordinate-descent for learning orthogonal matrices through Givens rotations , 2014, ICML.
[11] Yann LeCun,et al. Fast Approximation of Rotations and Hessians matrices , 2014, ArXiv.
[12] Ion Necoara,et al. Efficient random coordinate descent algorithms for large-scale structured nonconvex optimization , 2013, Journal of Global Optimization.
[13] Alexandr Andoni,et al. Practical and Optimal LSH for Angular Distance , 2015, NIPS.
[14] Sergey Levine,et al. Trust Region Policy Optimization , 2015, ICML.
[15] N. Pillai,et al. Kac's Walk on $n$-sphere mixes in $n\log n$ steps , 2015, 1507.08554.
[16] Tara N. Sainath,et al. Structured Transforms for Small-Footprint Deep Learning , 2015, NIPS.
[17] Sanjiv Kumar,et al. Binary embeddings with structured hashed projections , 2015, ICML.
[18] Sanjiv Kumar,et al. Orthogonal Random Features , 2016, NIPS.
[19] Yuan Yu,et al. TensorFlow: A system for large-scale machine learning , 2016, OSDI.
[20] Krzysztof Choromanski,et al. Recycling Randomness with Structure for Sublinear time Kernel Expansions , 2016, ICML.
[21] Xi Chen,et al. Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.
[22] Krzysztof Choromanski,et al. The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings , 2017, NIPS.
[23] Anne Morvan,et al. Structured adaptive and random spinners for fast machine learning computations , 2016, AISTATS.
[24] Jeffrey Pennington,et al. Nonlinear random matrix theory for deep learning , 2019, NIPS.
[25] Alec Radford,et al. Proximal Policy Optimization Algorithms , 2017, ArXiv.
[26] Surya Ganguli,et al. The Emergence of Spectral Universality in Deep Networks , 2018, AISTATS.
[27] Byron Boots,et al. Initialization matters: Orthogonal Predictive State Recurrent Neural Networks , 2018, ICLR.
[28] Richard E. Turner,et al. Structured Evolution with Compact Architectures for Scalable Policy Optimization , 2018, ICML.
[29] Richard E. Turner,et al. The Geometry of Random Features , 2018, AISTATS.
[30] Benjamin Recht,et al. Simple random search provides a competitive approach to reinforcement learning , 2018, ArXiv.
[31] Jascha Sohl-Dickstein,et al. Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks , 2018, ICML.
[32] Samuel S. Schoenholz,et al. Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks , 2018, ICML.