Mailing-List: contact user-help@mahout.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@mahout.apache.org
From: Grant Ingersoll <gsingers@apache.org>
Mime-Version: 1.0 (Apple Message framework v1251.1)
Content-Type: multipart/alternative;
 boundary="Apple-Mail=_140BBC93-896A-4D82-90D2-2A18259D25A5"
Subject: Re: SGD and memory
Date: Tue, 3 Jan 2012 22:58:29 -0500
In-Reply-To: 
 <CAJwFCa3MV8Q710F9VTWsfNdHYF1pnEouWx21k73FrMyJmPo+iQ@mail.gmail.com>
To: user@mahout.apache.org
References: <5F91F538-C239-427E-8C4F-EC2842D4DCC6@apache.org>
 <CAJwFCa3MV8Q710F9VTWsfNdHYF1pnEouWx21k73FrMyJmPo+iQ@mail.gmail.com>
Message-Id: <ECAF3B0A-695A-4984-A885-18499D1CB638@apache.org>

--Apple-Mail=_140BBC93-896A-4D82-90D2-2A18259D25A5
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
	charset=us-ascii


On Jan 3, 2012, at 5:59 PM, Ted Dunning wrote:

> You math is correct.
>=20
> When you say you have 105 features, what do you mean?

Sorry, that should have been 105 categories/labels.  I'm trying to do =
the ASF email equivalent of 20 news groups, but  in this case it's 105 =
ASF projects.  The basic task is to try and predict what project an =
email belongs to based on its content.

>  Are these textual
> features?  Or what?
>=20
> On Tue, Jan 3, 2012 at 2:53 PM, Grant Ingersoll <gsingers@apache.org> =
wrote:
>=20
>> I'm trying to run the full ASF email SGD classifier problem and am =
facing
>> heap size issues.  My current setup has 105 features and I am using a
>> cardinality of 100K.  I'm using the AdaptiveLogisticRegression.  I'm
>> getting heap errors and they occur when trying to construct the ALR =
class
>> (i.e. not later during training).
>>=20
>> Just trying to check my math on memory:
>> ALR comes with 20 CrossFoldLearners (CFL) and each of those comes =
with 5
>> OnlineLogisticRegression instances, which each have a DenseMatrix of
>> (numFeatures -1) X cardinality, plus some other vectors.
>>=20
>> This means, in my case, I have:
>> 20 x 5 x (104 x 100,000 x sizeof(double)) =3D 332,800,000,000 bits =3D =
~39 GB
>>=20
>> Am I understanding the major parts of memory for ALR correctly?  In =
other
>> words, I need to tone down the number of CFLs in the =
TrainASFEmail.java
>> file so as to not use 20 CFLs, right?


--Apple-Mail=_140BBC93-896A-4D82-90D2-2A18259D25A5--