Reorgnize and update table of contents

README.md

@@ -1,9 +1,15 @@
-# Scalable Machine Learning Systems
+# Fast and Scalable Machine Learning: Algorithms and  Systems
+===
 
-A collection of papers on scalable machine learning and systems, covering following topics:
+A collection of papers about recent progress on machine learning and systems, covering following topics:
 
-- [Distribtued Machine Learning](dist_ml.md)
-- [Deep Learning](deep_learning.md)
+1. [Distribtued Machine Learning](dist_ml.md)
+	- [Distributed Optimization](dist_ml.md#distributed-optimization)
+	- [Distributed ML System](dist_ml.md#distributed-ml-systems)
+2. [Deep Learning]()
+	- [Convolutioal Neural Networks](dl_cnn.md) 
+	- [Optimization](dl_opt.md)
+	- [Deep Learning Systems](dl_sys.md) 	
 - [Matrix Factorization](matrix_fact.md)
 - [Graph Computation](graph.md) 
 

dist_ml.md

@@ -1,11 +1,15 @@
-#Distributed Machine Learning
+# Distributed Machine Learning
+===
+
 
 ## Distributed Optimization
+---
 
+- 2016 KDD [Robust Large-Scale Machine Learning in the Cloud](http://www.kdd.org/kdd2016/papers/files/Paper_801.pdf)
 - 2015 KDD [Netowrk Lasso: Clustering and Optimization in Large
 Graphs](http://web.stanford.edu/~hallac/Network_Lasso.pdf)  
-
-##### Classic Distributed Learning
+- 2012 JMLR [Distributed Learning, Communication Complexity and Privacy](http://www.cs.cmu.edu/~avrim/Papers/DistLrn.pdf)  
+- 2012 AISTATS [Protocols for Learning Classifiers on Distributed Data](https://www.cs.utah.edu/~jeffp/papers/distrib-learn-AIStat.pdf)  
 - 2010 NIPS [Parallelized Stochastic Gradient Descent](http://martin.zinkevich.org/publications/nips2010.pdf) | [video](http://videosrv14.cs.washington.edu/info/videos/mp4/colloq/AAgarwal_140210.mp4) (One-Short)  
 - 2010 NAACL [Distributed Training Strategies for the Structured Perceptron](http://www.cslu.ogi.edu/~bedricks/courses/cs506-pslc/articles/week3/dpercep.pdf)   
 - 2009 NIPS [Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models](http://www.ryanmcd.com/papers/efficient_maxentNIPS2009.pdf)  
@@ -22,10 +26,11 @@ Graphs](http://web.stanford.edu/~hallac/Network_Lasso.pdf)
 - 2011 NIPS [Distributed Delayed Stochastic Optimization](http://papers.nips.cc/paper/4247-distributed-delayed-stochastic-optimization.pdf)  
 
 ##### Distributed Mini-Batching 
+<!--- 2015 [Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises](http://web.stanford.edu/group/pdplab/pdphandbook/)  -->
+- 2014 KDD [Efficient Mini-batch Training for Stochastic Optimization](http://www.cs.cmu.edu/~muli/file/minibatch_sgd.pdf)  
 - 2012 JMLR [Optimal Distributed Online Prediction Using Mini-Batches](http://jmlr.org/papers/volume13/dekel12a/dekel12a.pdf)  
 - 2011 ICML [Optimal Distributed Online Prediction](http://www.icml-2011.org/papers/404_icmlpaper.pdf)  
 - 2011 NIPS [Better Mini-Batch Algorithms via Accelerated Gradient Methods](http://papers.nips.cc/paper/4432-better-mini-batch-algorithms-via-accelerated-gradient-methods.pdf)  
-- 2015 [Explorations in Parallel Distributed Processing: A Handbook of Models, Programs, and Exercises](http://web.stanford.edu/group/pdplab/pdphandbook/)  
 
 
 ##### Distributed Consensus
@@ -36,29 +41,27 @@ Convergence Analysis and Network Scaling](http://www.eecs.berkeley.edu/~wainwrig
 - 2009 IEEE Trans. on Automatic Control [Distributed subgradient methods for multi-agent optimization](http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=4749425) | [slides](http://groups.csail.mit.edu/tds/seminars/s09/MIT-talk.pdf)  
 - 2008 Convex Optimization in Signal Processing and Communications [Cooperative Distributed Multi-Agent Optimization](https://asu.mit.edu/sites/default/files/documents/publications/Dist-chapter.pdf)  
 
-##### Parameter Server
-- 2014 NIPS [Communication Efficient Distributed Machine
-Learning with the Parameter Server](http://www.cs.cmu.edu/~muli/file/parameter_server_nips14.pdf)   
-- 2014 OSDI [Scaling Distributed Machine Learning with the Parameter Server](http://www.cs.cmu.edu/~muli/file/parameter_server_osdi14.pdf)  
-- 2013 NIPSW [Parameter Server for Distributed Machine Learning](http://www.cs.cmu.edu/~muli/file/ps.pdf)  
-- 2013 NIPSW [Distributed Delayed Proximal Gradient Methods](http://www.cs.cmu.edu/~muli/file/ddp.pdf)  
 
-##### MapReduce/AllReduce
+## Distributed ML Systems  
+---
+- 2014 APSys [A Scalable and Topology Configurable Protocol for Distributed Parameter Synchronization](http://research.microsoft.com/pubs/219927/main.pdf)  
+- 2014 ICML Tutorial [Emerging System for Large-Scale Machine Learning](http://www.cs.berkeley.edu/~jegonzal/talks/icml14_sysml.pdf)  
+- 2013 Distributed Computing [When distributed computation is communication expensive](http://arxiv.org/abs/1304.4636)    
+
+##### MapReduce / AllReduce
 - 2014 JMLR [A Reliable Effective Terascale Linear Learning System](http://jmlr.org/papers/volume15/agarwal14a/agarwal14a.pdf)  
 - 2010 NIPSW [MapReduce/Bigtable for Distributed Optimization](http://www.australianscience.com.au/research/google/36948.pdf)[slides](http://lccc.eecs.berkeley.edu/Slides/HallGiMa10_slides.pdf)  
 - 2007 NIPS [Map-Reduce for Machine Learning on Multicore](http://machinelearning.wustl.edu/mlpapers/paper_files/NIPS2006_725.pdf)  
 
-## ML Systems  
-- 2015 EuroSys [MALT: Distributed Data-Parallelism for Existing ML Applications](http://www.nec-labs.com/~asim/papers/malt_eurosys15.pdf)  
-2014 OSDI [Scaling Distributed Machine Learning with the Parameter Server](http://www.cs.cmu.edu/~muli/file/parameter_server_osdi14.pdf)  
-- 2014 JMLR [A Reliable Effective Terascale Linear Learning System](http://jmlr.org/papers/volume15/agarwal14a/agarwal14a.pdf)  
-- 2014 APSys [A Scalable and Topology Configurable Protocol for Distributed Parameter Synchronization](http://research.microsoft.com/pubs/219927/main.pdf)  
-- 2014 ICML Tutorial [Emerging System for Large-Scale Machine Learning](http://www.cs.berkeley.edu/~jegonzal/talks/icml14_sysml.pdf)  
-- 2012 EuroSys [MadLINQ: Large-Scale Distributed Matrix Computation for the Cloud](http://research.microsoft.com/pubs/158914/euro135-qian.pdf)  
-- 2008 OSDI [DryadLINQ: A System for General-Purpose Distributed Data-Parallel Computing Using a High-Level Language](http://research.microsoft.com/en-us/projects/dryadlinq/dryadlinq.pdf)   
-
+##### Parameter Servers
+- 2014 OSDI [Project Adam: Building an Efficient and Scalable Deep Learning Training System](https://www.usenix.org/system/files/conference/osdi14/osdi14-paper-chilimbi.pdf)  	 
+- 2014 OSDI [Scaling Distributed Machine Learning with the Parameter Server](http://www.cs.cmu.edu/~muli/file/parameter_server_osdi14.pdf)  
+- 2014 NIPS [Communication Efficient Distributed Machine
+Learning with the Parameter Server](http://www.cs.cmu.edu/~muli/file/parameter_server_nips14.pdf)   
+- 2013 NIPSW [Parameter Server for Distributed Machine Learning](http://www.cs.cmu.edu/~muli/file/ps.pdf)  
+- 2013 NIPSW [Distributed Delayed Proximal Gradient Methods](http://www.cs.cmu.edu/~muli/file/ddp.pdf)  
+- 2012 NIPS [Large Scale Distributed Deep Networks](http://static.googleusercontent.com/media/research.google.com/en/us/archive/large_deep_networks_nips2012.pdf) (DistBelief)  
+- 2010 VLDB [An Architecture for Parallel Topic Models](http://vldb.org/pvldb/vldb2010/papers/R63.pdf)  
 
-##### Data Privacy
-- 2012 JMLR [Distributed Learning, Communication Complexity and Privacy](http://www.cs.cmu.edu/~avrim/Papers/DistLrn.pdf)  
-- 2012 AISTATS [Protocols for Learning Classifiers on Distributed Data](https://www.cs.utah.edu/~jeffp/papers/distrib-learn-AIStat.pdf)  
-- 2013 Distributed Computing [When distributed computation is communication expensive](http://arxiv.org/abs/1304.4636)    
+##### Peer-to-Peer
+- 2015 EuroSys [MALT: Distributed Data-Parallelism for Existing ML Applications](http://www.nec-labs.com/~asim/papers/malt_eurosys15.pdf)  

graph.md

@@ -1,4 +1,5 @@
-#Large-Scale Graph Computation
+# Large-Scale Graph Computation
+===
 
 2015 CIKM [HDRF: Stream-Based Partitioning for Power-Law Graphs](http://www.fabiopetroni.com/Download/petroni2015HDRF.pdf)  
 2015 VLDB [One Trillion Edges: Graph Processing at Facebook-Scale](http://www.vldb.org/pvldb/vol8/p1804-ching.pdf)  

matrix_fact.md

@@ -1,4 +1,5 @@
 # Matrix Factorization
+===
 
 - 2016 WSDM [DiFacto — Distributed Factorization Machines](http://www.cs.cmu.edu/~yuxiangw/docs/fm.pdf)   
 - 2015 CIKM [HDRF: Stream-Based Partitioning for Power-Law Graphs](http://www.fabiopetroni.com/Download/petroni- 2015HDRF.pdf)