1. parallelLDA contains various implementation of multi threaded LDA
2. singleLDA contains various implementation of single threaded LDA
3. topwords a tool to explore topics learnt by the LDA/HDP
4. perplexity a tool to calculate perplexity on another dataset using word|topic matrix
5. datagen packages txt files for our program
6. preprocessing for converting from UCI or cLDA to simple txt file having one document per line

1. All codes are under src within respective folder
2. For running Topic Models many template scripts are provided under scripts
3. data is a placeholder folder where to put the data
4. build and dist folder will be created to hold the executables

1. gcc >= 5.0 or Intel® C++ Compiler 2016 for using C++14 features
2. split >= 8.21 (part of GNU coreutils)

We will show how to run our LDA on an UCI bag of words dataset

1. First of all compile by hitting make

    make

2. Download example dataset from UCI repository. For this a script has been provided.

    scripts/get_data.sh

3. Prepare the data for our program

    scripts/prepare.sh data/nytimes 1

   For other datasets replace nytimes with dataset name or location.

4. Run LDA!

    scripts/lda_runner.sh

   Inside the lda_runner.sh all the parameters e.g. number of topics, hyperparameters of the LDA, number of threads etc. can be specified. By default the outputs are stored under out/. Also you can specify which inference algorithm of LDA you want to run:

   1. simpleLDA: Plain vanilla Gibbs sampling by Griffiths04
   2. sparseLDA: Sparse LDA of Yao09
   3. aliasLDA: Alias LDA
   4. FTreeLDA: F++LDA (inspired from Yu14
   5. lightLDA: light LDA of Yuan14

The make file has some useful features:

• if you have Intel® C++ Compiler, then you can instead

   make intel

• or if you want to use Intel® C++ Compiler's cross-file optimization (ipo), then hit

   make inteltogether

• Also you can selectively compile individual modules by specifying

   make <module-name>

• or clean individually by

   make clean-<module-name>

Based on our evaluation F++LDA works the best in terms of both speed and perplexity on a held-out dataset. For example on Amazon EC2 c4.8xlarge, we obtained more than 25 million/tokens per second. Below we provide performance comparison against various inference procedures on publicaly available datasets.

Experimental datasets and their statistics. V denotes vocabulary size, L denotes the number of training tokens, D denotes the number of documents, L/V indicates the average number of occurrences of a word, L/D indicates the average length of a document.