Changyou Chen

• Home
• Publication
• Code
• Contact
• Courses

Santa: a Stochastic Optimization Algorithm for Deep Learning

We have three versions for the Santa algorithm: a MATLAB version for feedforward neural networks and convolutional neural networks, a Python version for recurrent neural networks, and a Caffe version for scalable learning implemented in C++. Please refer to the code for details.

Reference

• Changyou Chen, David Carlson, Zhe Gan, Chunyuan Li, Lawrence Carin.
  Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization,
  International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, 2016.

---

Symmetric Splitting Integrators for Stochastic Gradient MCMC

This is a MATLAB implementation for the symmetric splitting integrators to improve convergence rates of SG-MCMC algorithms.

Reference

• Changyou Chen, Nan Ding, Lawrence Carin.
  On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators,
  Neural Information Processing Systems (NIPS), Montreal, Canada, 2015.

---

Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data

This is a MATLAB implementation for Scalable Bayesian Non-Negative Tensor Factorization.

Reference

• Changwei Hu, Piyush Rai, Changyou Chen, Matthew Harding, Lawrence Carin.
  Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data.
  European Conference on Machine Learning (ECML), 2015.

---

Scalable Deep Poisson Factor Analysis for Topic Modeling

This is a MATLAB implementation for Scalable Deep Poisson Factor Analysis.

Reference

• Zhe Gan, Changyou Chen, Ricardo Henao, David Carlson, Lawrence Carin.
  Scalable Deep Poisson Factor Analysis for Topic Modeling.
  International Conference on Machine Learning (ICML), Lille, France, 2015.

---

Stochastic Gradient Thermostats

This is a C++ implementation for stochastic gradient thermostats, applied for latent Dirichlet allocation (LDA).

Reference

• Nan Ding, Youhan Fang, Ryan Babbush, Changyou Chen, Robert Skeel, Hartmut Neven.
  Bayesian Sampling Using Stochastic Gradient Thermostats.
  Neural Information Processing Systems (NIPS), Montreal, Canada, 2014.

---

Bayesian Max-Margin Clustering

This is a C++ implementation for Bayesian max-margin clustering, applied for cluster topic models.

Reference

• Changyou Chen, Jun Zhu, Xinhua Zhang.
  Bayesian Nonparametric Max-margin Clustering.
  Neural Information Processing Systems (NIPS), Montreal, Canada, 2014.

---

Differential Topic Models

This is a C++ implementation for differential topic models.

Reference

• Changyou Chen, Wray Buntine, Nan Ding, Lexing Xie, Lan Du.
  Differential Topic Models.
  IEEE Transactions on Pattern Recognition and Machine Intelligence (TPAMI), vol. 37, no. 2, pp. 230–242, 2015.

---

Dependent Normalized Random Measures

This is a MATLAB implementation with C++ mex to accelerate sampling for dependent normalized random measures.

Reference

• Changyou Chen, Vinayak Rao, Wray Buntine, Yee Whye Teh.
  Dependent Normalized Random Measures.
  International Conference on Machine Learning (ICML), Atlanta, USA, 2013.

---

Design by Mark Reid, (Some rights reserved)
Powered by Jekyll, Pandoc, MathJax