spark-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Burak Yavuz <>
Subject Re: 15 new MLlib algorithms
Date Wed, 09 Jul 2014 19:31:29 GMT

The roadmap for the 1.1 release and MLLib includes algorithms such as:

Non-negative matrix factorization, Sparse SVD, Multiclass 
decision tree, Random Forests (?)

and optimizers such as:
ADMM, Accelerated gradient methods

also a statistical toolbox that includes:
descriptive statistics, sampling, hypothesis testing

and hopefully Parallel model training for autotuning.



----- Original Message -----
From: "Michael Malak" <>
Sent: Wednesday, July 9, 2014 11:43:26 AM
Subject: 15 new MLlib algorithms

At Spark Summit, Patrick Wendell indicated the number of MLlib algorithms would "roughly double"
in 1.1 from the current approx. 15.

What are the planned additional algorithms?

In Jira, I only see two when filtering on version 1.1, component MLlib: one on multi-label
and another on high dimensionality.

View raw message