Tensor Methods for Generating Compact Uncertainty Quantification and Deep Learning Models

Tensor methods have become a promising tool to solve high-dimensional problems in the big data era. By exploiting possible low-rank tensor factorization, many high-dimensional model-based or data-driven problems can be solved to facilitate decision making or machine learning. In this paper, we summarize the recent applications of tensor computation in obtaining compact models for uncertainty quantification and deep learning. In uncertainty analysis where obtaining data samples is expensive, we show how tensor methods can significantly reduce the simulation or measurement cost. To enable the deployment of deep learning on resource-constrained hardware platforms, tensor methods can be used to significantly compress an over-parameterized neural network model or directly train a small-size model from scratch via optimization or statistical techniques. Recent Bayesian tensorized neural networks can automatically determine their tensor ranks in the training process.

[1]  Lawrence T. Pileggi,et al.  PRIMA: passive reduced-order interconnect macromodeling algorithm , 1997, ICCAD 1997.

[2]  R. Ghanem,et al.  Stochastic Finite Elements: A Spectral Approach , 1990 .

[3]  Alexander Novikov,et al.  Tensorizing Neural Networks , 2015, NIPS.

[4]  Satoshi Nakamura,et al.  Tensor Decomposition for Compressing Recurrent Neural Network , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[5]  Tsui-Wei Weng,et al.  Big-Data Tensor Recovery for High-Dimensional Uncertainty Quantification of Process Variations , 2017, IEEE Transactions on Components, Packaging and Manufacturing Technology.

[6]  Rob A. Rutenbar,et al.  Practical, fast Monte Carlo statistical static timing analysis: why and how , 2008, ICCAD 2008.

[7]  Alberto L. Sangiovanni-Vincentelli,et al.  Steady-state methods for simulating analog and microwave circuits , 1990, The Kluwer international series in engineering and computer science.

[8]  Andrzej Cichocki,et al.  Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysis , 2014, IEEE Signal Processing Magazine.

[9]  Jacob K. White,et al.  A trajectory piecewise-linear approach to model order reduction and fast simulation of nonlinear circuits and micromachined devices , 2001, IEEE/ACM International Conference on Computer Aided Design. ICCAD 2001. IEEE/ACM Digest of Technical Papers (Cat. No.01CH37281).

[10]  Alexander Novikov,et al.  Ultimate tensorization: compressing convolutional and FC layers alike , 2016, ArXiv.

[11]  Bruno Sudret,et al.  Global sensitivity analysis using low-rank tensor approximations , 2016, Reliab. Eng. Syst. Saf..

[12]  Satoshi Nakamura,et al.  Compressing recurrent neural network with tensor train , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[13]  Danilo P. Mandic,et al.  Tucker Tensor Layer in Fully Connected Neural Networks , 2019, ArXiv.

[14]  Chunfeng Cui,et al.  High-Dimensional Uncertainty Quantification of Electronic and Photonic IC With Non-Gaussian Correlated Process Variations , 2019, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[15]  Jacob K. White,et al.  A multiparameter moment-matching model-reduction approach for generating geometrically parameterized interconnect performance models , 2004, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[16]  Masashi Sugiyama,et al.  Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 2 Applications and Future Perspectives , 2017, Found. Trends Mach. Learn..

[17]  V. Okhmatovski,et al.  Tensor Train Accelerated Solution of Volume Integral Equation for 2-D Scattering Problems and Magneto-Quasi-Static Characterization of Multiconductor Transmission Lines , 2019, IEEE Transactions on Microwave Theory and Techniques.

[18]  Tsui-Wei Weng,et al.  A big-data approach to handle process variations: Uncertainty quantification by tensor recovery , 2016, 2016 IEEE 20th Workshop on Signal and Power Integrity (SPI).

[19]  Hong Yan,et al.  A quadratic penalty method for hypergraph matching , 2017, Journal of Global Optimization.

[20]  Jacob K. White,et al.  A precorrected-FFT method for electrostatic analysis of complicated 3-D structures , 1997, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[21]  Giovanni Marucci,et al.  Stochastic testing simulator for integrated circuits and MEMS: Hierarchical and sparse techniques , 2014, Proceedings of the IEEE 2014 Custom Integrated Circuits Conference.

[22]  Anima Anandkumar,et al.  Tensor Contraction Layers for Parsimonious Deep Nets , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[23]  Ngai Wong,et al.  Model Reduction and Simulation of Nonlinear Circuits via Tensor Decomposition , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[24]  Ivan Oseledets,et al.  Tensor-Train Decomposition , 2011, SIAM J. Sci. Comput..

[25]  Lorien Y. Pratt,et al.  Comparing Biases for Minimal Network Construction with Back-Propagation , 1988, NIPS.

[26]  Johan Håstad,et al.  Tensor Rank is NP-Complete , 1989, ICALP.

[27]  Andrzej Cichocki,et al.  Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions , 2016, Found. Trends Mach. Learn..

[28]  Lijun Jiang,et al.  STAVES: Speedy tensor-aided Volterra-based electronic simulator , 2015, 2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[29]  Peng Li,et al.  Parallel Circuit Simulation: A Historical Perspective and Recent Developments , 2012, Found. Trends Electron. Des. Autom..

[30]  Zheng Zhang,et al.  Prediction of Multidimensional Spatial Variation Data via Bayesian Tensor Completion , 2019, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[31]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[32]  Xiu Yang,et al.  Enabling High-Dimensional Hierarchical Uncertainty Quantification by ANOVA and Tensor-Train Decomposition , 2014, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[33]  Mattan Kamon,et al.  FASTHENRY: a multipole-accelerated 3-D inductance extraction program , 1994 .

[34]  Dongbin Xiu,et al.  The Wiener-Askey Polynomial Chaos for Stochastic Differential Equations , 2002, SIAM J. Sci. Comput..

[35]  Zheng Zhang,et al.  Stochastic Collocation with Non-Gaussian Correlated Parameters via a New Quadrature Rule , 2018, 2018 IEEE 27th Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS).

[36]  Andrzej Cichocki,et al.  MUSCO: Multi-Stage Compression of neural networks , 2019 .

[37]  Dongbin Xiu,et al.  High-Order Collocation Methods for Differential Equations with Random Inputs , 2005, SIAM J. Sci. Comput..

[38]  Liqing Zhang,et al.  Bayesian CP Factorization of Incomplete Tensors with Automatic Rank Determination , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Dilin Wang,et al.  Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm , 2016, NIPS.

[40]  Rob A. Rutenbar,et al.  Virtual Probe: A Statistical Framework for Low-Cost Silicon Characterization of Nanoscale Integrated Circuits , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[41]  Danilo P. Mandic,et al.  Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation , 2019 .

[42]  Luca Daniel,et al.  Stochastic Testing Method for Transistor-Level Uncertainty Quantification Based on Generalized Polynomial Chaos , 2013, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[43]  R. Saleh FastCap : A Multipole Accelerated 3-D Capacitance Extraction Program , 1991 .

[44]  Andrzej Cichocki,et al.  One time is not enough: iterative tensor decomposition for neural network compression , 2019, ArXiv.

[45]  Geoffrey E. Hinton,et al.  Keeping the neural networks simple by minimizing the description length of the weights , 1993, COLT '93.

[46]  Eunhyeok Park,et al.  Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications , 2015, ICLR.

[47]  Jieping Ye,et al.  Tensor Completion for Estimating Missing Values in Visual Data , 2013, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  Zheng Zhang,et al.  Uncertainty Quantification of Electronic and Photonic ICs with Non-Gaussian Correlated Process Variations , 2018, 2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[49]  F. L. Hitchcock The Expression of a Tensor or a Polyadic as a Sum of Products , 1927 .

[50]  Zemin Zhang,et al.  Exact Tensor Completion Using t-SVD , 2015, IEEE Transactions on Signal Processing.

[51]  J. Jeffry Howbert,et al.  PREDICTD: PaRallel Epigenomics Data Imputation with Cloud-based Tensor Decomposition , 2017, bioRxiv.

[52]  Nikos D. Sidiropoulos,et al.  Tensor Decomposition for Signal Processing and Machine Learning , 2016, IEEE Transactions on Signal Processing.

[53]  Zheng Zhang,et al.  Bayesian Tensorized Neural Networks with Automatic Rank Selection , 2019, Neurocomputing.

[54]  B. Sudret,et al.  Reliability analysis of high-dimensional models using low-rank tensor approximations , 2016, 1606.08577.

[55]  Dries Vande Ginste,et al.  Stochastic Modeling of Nonlinear Circuits via SPICE-Compatible Spectral Equivalents , 2014, IEEE Transactions on Circuits and Systems I: Regular Papers.

[56]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[57]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[58]  Ivan V. Oseledets,et al.  Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition , 2014, ICLR.

[59]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[60]  Zheng Zhang,et al.  Stochastic Collocation With Non-Gaussian Correlated Process Variations: Theory, Algorithms, and Applications , 2018, IEEE Transactions on Components, Packaging and Manufacturing Technology.