[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [amibroker] The EASIEST way to use new optimizer engines



PureBytes Links

Trading Reference Links

...but I'm still a bit confused.  If we use the default solver -- that is, 
we don't put an optimizerset = line in, then we get an exhaustive search, 
right.  Every possible combination of values is tested and compared. 
Wouldn't that be the best solution if it's possible in a reasonable 
timeframe?

So, what happens when the cmae optimizer is used instead?  Something like 
this?

1.  AB computes CAR/MDD from the default values of the optimizing variables
2.  AB computes CAR/MDD from another set of optimizing variables
3.  1 and 2 are sent to the optimizer, and it returns a set of variables to 
try next.
4.  Repeat 2 and 3 until a solution is reached?

Sorry, but this is pretty new to me.



----- Original Message ----- 
From: "Tomasz Janeczko" <groups@xxxxxxxxxxxxx>
To: <amibroker@xxxxxxxxxxxxxxx>
Sent: Friday, June 27, 2008 2:33 PM
Subject: Re: [amibroker] The EASIEST way to use new optimizer engines


> Hello,
>
> Yes these are different solvers.
> In principle only exhaustive search is guaranteed to find global optimum 
> value.
>
> Non-exhaustive (or "intelligent") methods will find global or local 
> optimum.
> The goal is of course to find global one, but if there is a single sharp 
> peak
> out of zillions parameter combinations, non-exhaustive methods may fail
> to find this single peak, but taking it form trader's perspecive, finding 
> single sharp peak
> is useless for trading because that result would be instable (too fragile) 
> and
> not replicable in real trading. In optimization process we are rather 
> looking
> for plateau regions with stable parameters and this is the area where 
> intelligent methods shine.
>
> Best regards,
> Tomasz Janeczko
> amibroker.com
> ----- Original Message ----- 
> From: "cstrader" <cstrader232@xxxxxxxxxxxx>
> To: <amibroker@xxxxxxxxxxxxxxx>
> Sent: Friday, June 27, 2008 8:25 PM
> Subject: Re: [amibroker] The EASIEST way to use new optimizer engines
>
>
>> Thanks, that helps... basically these are all different variations of
>> "solvers," right?  And they don't care what they are modelling -- they 
>> just
>> do the math looking for the single best solution?  So it's just speed 
>> that
>> matters?  Or do different solvers get different solutions?
>>
>> And I echo all of the recent praises... take care of yourself Tomasz!
>>
>> Chuck
>>
>> ----- Original Message ----- 
>> From: "Tomasz Janeczko" <groups@xxxxxxxxxxxxx>
>> To: <amibroker@xxxxxxxxxxxxxxx>
>> Sent: Friday, June 27, 2008 2:05 PM
>> Subject: Re: [amibroker] The EASIEST way to use new optimizer engines
>>
>>
>>> Hello,
>>>
>>> These are general-purpose optimization algorithms of non-linear 
>>> functions.
>>> Any trading system is a function of certain number of arguments. The
>>> inputs
>>> are parameters and quotation data , the output is your optimization 
>>> target
>>> (say CAR/MDD). And you are looking for maximum of given function.
>>>
>>> I provided links to scientific articles describing the math that is
>>> underlying these algorithms
>>> - see the README file
>>> http://www.amibroker.com/devlog/wp-content/uploads/2008/06/readme5130.html
>>>
>>> Some are based on nature (animal behavior) - PSO algorithm,
>>> or biological process - Genetic algorithms,
>>> and some are based on mathematical concepts derived by humans - CMA-ES.
>>>
>>> These algorithms are used in many different areas, including finance.
>>>
>>> Enter "PSO finance" or "CMA-ES finance" in Google and you will find lots
>>> of info.
>>>
>>> Best regards,
>>> Tomasz Janeczko
>>> amibroker.com
>>> ----- Original Message ----- 
>>> From: "cstrader" <cstrader232@xxxxxxxxxxxx>
>>> To: <amibroker@xxxxxxxxxxxxxxx>
>>> Sent: Friday, June 27, 2008 7:39 PM
>>> Subject: Re: [amibroker] The EASIEST way to use new optimizer engines
>>>
>>>
>>>> Yes, and more generally, what are these systems?  They seem to mimic
>>>> evolutionary processes... how are they applied to optimization?  And 
>>>> how
>>>> do
>>>> we know that they work well for our particular needs -- are financial
>>>> markets and Darwinian evolution really the same processes?  Any 
>>>> sources,
>>>> references appreciated.
>>>>
>>>> Thanks
>>>>
>>>>
>>>>
>>>> ----- Original Message ----- 
>>>> From: "Thomas Ludwig" <Thomas.Ludwig@xxxxxx>
>>>> To: <amibroker@xxxxxxxxxxxxxxx>
>>>> Sent: Friday, June 27, 2008 12:43 PM
>>>> Subject: Re: [amibroker] The EASIEST way to use new optimizer engines
>>>>
>>>>
>>>>> TJ,
>>>>>
>>>>> the new engines work very well. But just one question:
>>>>>
>>>>>> (the best one which is  CMA-ES).
>>>>>
>>>>> Are there still cases where the other engines are preferable? I mean
>>>>> there must be a reason why you included them ;-)
>>>>>
>>>>> Best regards,
>>>>>
>>>>> Thomas
>>>>>
>>>>> ------------------------------------
>>>>>
>>>>> Please note that this group is for discussion between users only.
>>>>>
>>>>> To get support from AmiBroker please send an e-mail directly to
>>>>> SUPPORT {at} amibroker.com
>>>>>
>>>>> For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
>>>>> http://www.amibroker.com/devlog/
>>>>>
>>>>> For other support material please check also:
>>>>> http://www.amibroker.com/support.html
>>>>> Yahoo! Groups Links
>>>>>
>>>>>
>>>>>
>>>>
>>>>
>>>> ------------------------------------
>>>>
>>>> Please note that this group is for discussion between users only.
>>>>
>>>> To get support from AmiBroker please send an e-mail directly to
>>>> SUPPORT {at} amibroker.com
>>>>
>>>> For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
>>>> http://www.amibroker.com/devlog/
>>>>
>>>> For other support material please check also:
>>>> http://www.amibroker.com/support.html
>>>> Yahoo! Groups Links
>>>>
>>>>
>>>>
>>>
>>> ------------------------------------
>>>
>>> Please note that this group is for discussion between users only.
>>>
>>> To get support from AmiBroker please send an e-mail directly to
>>> SUPPORT {at} amibroker.com
>>>
>>> For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
>>> http://www.amibroker.com/devlog/
>>>
>>> For other support material please check also:
>>> http://www.amibroker.com/support.html
>>> Yahoo! Groups Links
>>>
>>>
>>>
>>
>>
>> ------------------------------------
>>
>> Please note that this group is for discussion between users only.
>>
>> To get support from AmiBroker please send an e-mail directly to
>> SUPPORT {at} amibroker.com
>>
>> For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
>> http://www.amibroker.com/devlog/
>>
>> For other support material please check also:
>> http://www.amibroker.com/support.html
>> Yahoo! Groups Links
>>
>>
>>
>
> ------------------------------------
>
> Please note that this group is for discussion between users only.
>
> To get support from AmiBroker please send an e-mail directly to
> SUPPORT {at} amibroker.com
>
> For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
> http://www.amibroker.com/devlog/
>
> For other support material please check also:
> http://www.amibroker.com/support.html
> Yahoo! Groups Links
>
>
>


------------------------------------

Please note that this group is for discussion between users only.

To get support from AmiBroker please send an e-mail directly to 
SUPPORT {at} amibroker.com

For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
http://www.amibroker.com/devlog/

For other support material please check also:
http://www.amibroker.com/support.html
Yahoo! Groups Links

<*> To visit your group on the web, go to:
    http://groups.yahoo.com/group/amibroker/

<*> Your email settings:
    Individual Email | Traditional

<*> To change settings online go to:
    http://groups.yahoo.com/group/amibroker/join
    (Yahoo! ID required)

<*> To change settings via email:
    mailto:amibroker-digest@xxxxxxxxxxxxxxx 
    mailto:amibroker-fullfeatured@xxxxxxxxxxxxxxx

<*> To unsubscribe from this group, send an email to:
    amibroker-unsubscribe@xxxxxxxxxxxxxxx

<*> Your use of Yahoo! Groups is subject to:
    http://docs.yahoo.com/info/terms/