Trjtdtk

Air travel with refrigerated insulin

PTIJ: Which Dr. Seuss books should one obtain?

Naïve RSA decryption in Python

Hot air balloons as primitive bombers

What do the positive and negative (+/-) transmit and receive pins mean on Ethernet cables?

Why is the intercept typed in as a 1 in stats packages (R, python)

What should be the ideal length of sentences in a blog post for ease of reading?

Can other pieces capture a threatening piece and prevent a checkmate?

What's the meaning of "what it means for sth to be sth"?

Does fire aspect on a sword destroy mob drops?

Why is "la Gestapo" feminine?

Why didn’t Eve recognize the little cockroach as a living organism?

Mortal danger in mid-grade literature

Exit shell with shortcut (not typing exit) that closes session properly

What is this high flying aircraft over Pennsylvania?

Magento 1 : each() function is deprecated

Why doesn't the fusion process of the sun speed up?

Magento 2: Make category field required in product form in backend

Exposing a company lying about themselves in a tightly knit industry (videogames) : Is my career at risk on the long run?

Put the phone down / Put down the phone

Would mining huge amounts of resources on the Moon change its orbit?

When doing an engine swap , do you have to have a matching ecu

How to left align the cases in Latex?

How can an organ that provides biological immortality be unable to regenerate?

Probabilistic guarantees for SQL query execution

Data manipulation in SQLHow do I write a SQL (or dwSQL) query across these two different datasets?Sql satament sql serverSpark SQL Pivot CrossTab functionalitySQL Server and skip first n rowsData dashboard for SQL server databaseNot enough replicas available for query at consistency all (2 required but only 1 alive)Natural Language to SQL queryCall a SQL procedure, for each group byPython-SQL database

1

$begingroup$

We are working on a project that tries to accelerate Spark SQL using dedicated hardware.
Our approach works much better (in terms of the resulting latency) if we allow query processing that is only probably correct.

That is, with high probability (e.g., 99.9%) we will return the correct answer.

I was wondering if such there are any existing systems with such a guarantee. The closest I've seen is the "approximate percentile" computation, but this also has an error in the result (whereas we give the exact result with high probability).

Thanks!

bigdata apache-spark probability sql

share|improve this question

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

1

$begingroup$

We are working on a project that tries to accelerate Spark SQL using dedicated hardware.
Our approach works much better (in terms of the resulting latency) if we allow query processing that is only probably correct.

That is, with high probability (e.g., 99.9%) we will return the correct answer.

I was wondering if such there are any existing systems with such a guarantee. The closest I've seen is the "approximate percentile" computation, but this also has an error in the result (whereas we give the exact result with high probability).

Thanks!

bigdata apache-spark probability sql

share|improve this question

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

We are working on a project that tries to accelerate Spark SQL using dedicated hardware.
Our approach works much better (in terms of the resulting latency) if we allow query processing that is only probably correct.

That is, with high probability (e.g., 99.9%) we will return the correct answer.

I was wondering if such there are any existing systems with such a guarantee. The closest I've seen is the "approximate percentile" computation, but this also has an error in the result (whereas we give the exact result with high probability).

Thanks!

bigdata apache-spark probability sql

share|improve this question

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked yesterday

JennyJenny

61

New contributor

Jenny is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked yesterday

JennyJenny

61