GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

In this work we present a new method of black-box optimization and constraint satisfaction. Existing algorithms that have attempted to solve this problem are unable to consider multiple modes, and are not able to adapt to changes in environment dynamics. To address these issues, we developed a modified Cross-Entropy Method (CEM) that uses a masked auto-regressive neural network for modeling uniform distributions over the solution space. We train the model using maximum entropy policy gradient methods from Reinforcement Learning. Our algorithm is able to express complicated solution spaces, thus allowing it to track a variety of different solution regions. We empirically compare our algorithm with variations of CEM, including one with a Gaussian prior with fixed variance, and demonstrate better performance in terms of: number of diverse solutions, better mode discovery in multi-modal problems, and better sample efficiency in certain cases.

[1]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[2]  Reuven Y. Rubinstein,et al.  Optimization of computer simulation models with rare events , 1997 .

[3]  R. Rubinstein The Cross-Entropy Method for Combinatorial and Continuous Optimization , 1999 .

[4]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[5]  Shie Mannor,et al.  A Tutorial on the Cross-Entropy Method , 2005, Ann. Oper. Res..

[6]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[7]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[8]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[9]  Hugo Larochelle,et al.  MADE: Masked Autoencoder for Distribution Estimation , 2015, ICML.

[10]  Nikolaus Hansen,et al.  The CMA Evolution Strategy: A Tutorial , 2016, ArXiv.

[11]  Samy Bengio,et al.  Density estimation using Real NVP , 2016, ICLR.

[12]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

[13]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

[14]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[15]  Vladimir Stojanovic,et al.  BagNet: Berkeley Analog Generator with Layout Optimizer Boosted with Deep Neural Networks , 2019, 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[16]  S. Geyer,et al.  Cross entropy-based importance sampling using Gaussian densities revisited , 2019, Structural Safety.

[17]  Dina Katabi,et al.  Circuit-GNN: Graph Neural Networks for Distributed Circuit Design , 2019, ICML.

[18]  B. Nikolić,et al.  AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs , 2020, 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE).