177 lines
8.5 KiB
TeX
177 lines
8.5 KiB
TeX
%root: main.tex
|
|
%!TEX root = ./main.tex
|
|
%\onecolumn
|
|
\subsection{Reduced Polynomials and Equivalences}
|
|
|
|
We now introduce some terminology % for polynomials
|
|
and develop a reduced form of lineage polynomials for a \abbrBIDB or \abbrTIDB.
|
|
%We will use $(X + Y)^2$ as a running example.
|
|
Note that a polynomial over $\vct{X}=(X_1,\dots,X_n)$ with individual degree $B <\infty$
|
|
%\footnote{The standard definition of polynomials requires a finite number of terms.} and $c_\vct{i} \in \domN$
|
|
is formally defined as: %(with $c_\vct{i} \in \domN$):
|
|
\begin{equation}
|
|
\label{eq:sop-form}
|
|
\poly\inparen{X_1,\dots,X_n}=\sum_{\vct{d}\in\{0,\ldots,B\}^n} c_{\vct{d}}\cdot \prod_{i=1}^n X_i^{d_i},
|
|
\end{equation}
|
|
where $c_{\vct{d}}\in \semN$.
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
\begin{Definition}[Standard Monomial Basis]\label{def:smb}
|
|
From above, the term $\prod_{i=1}^n X_i^{d_i}$ is a {\em monomial}. A polynomial $\poly\inparen{\vct{X}}$ is in standard monomial basis (\abbrSMB) when we keep only the terms with $c_{\vct{d}}\ne 0$ from \Cref{eq:sop-form}.
|
|
\end{Definition}
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
Unless othewise noted, we consider all polynomials to be in \abbrSMB representation.
|
|
When it is unclear, we use $\smbOf{\poly}$ to denote the \abbrSMB form of a polynomial $\poly$.
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
\begin{Definition}[Degree]\label{def:degree}
|
|
The degree of polynomial $\poly(\vct{X})$ is the largest $\sum_{i=1}^n d_i$ such that $c_{(d_1,\dots,d_n)}\ne 0$. % maximum sum of exponents, over all monomials in $\smbOf{\poly(\vct{X})}$.
|
|
\end{Definition}
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
As an example, the degree of the polynomial $X^2+2XY^2+Y^2$ is $3$.
|
|
Product terms in lineage arise only from join operations (\Cref{fig:nxDBSemantics}), so intuitively, the degree of a lineage polynomial is analogous to the largest number of joins to produce an output tuple.
|
|
%in any clause of the $\raPlus$ query that created it.
|
|
We call a polynomial $\poly\inparen{\vct{X}}$ a \emph{\bi-lineage polynomial} (resp., \emph{\ti-lineage polynomial}, or simply lineage polynomial), if there exists a $\raPlus$ query $\query$, \bi (\ti) $\pdb$, and tuple $\tup$ such that $\poly\inparen{\vct{X}} = \apolyqdt\inparen{\vct{X}}.$
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%\begin{Definition}[Modding with a set]\label{def:mod-set}
|
|
%Let $S$ be a {\em set} of polynomials over $\vct{X}$. Then $\poly(\vct{X})\mod{S}$ is the polynomial obtained by taking the mod of $\poly(\vct{X})$ over {\em all} polynomials in $S$ (order does not matter).
|
|
%\end{Definition}
|
|
%For example for a set of polynomials $S=\inset{X^2-X, Y^2-Y}$, taking the polynomial $2X^2 + 3XY - 2Y^2\mod S$ yields $2X+3XY-2Y$.
|
|
%%
|
|
%\begin{Definition}[$\mathcal B$, $\mathcal T$]\label{def:mod-set-polys}
|
|
%Given the set of BIDB variables $\inset{X_{i,j}}$, define
|
|
%
|
|
%\setlength\parindent{0pt}
|
|
%\vspace*{-3mm}
|
|
%{\small
|
|
%\begin{tabular}{@{}l l}
|
|
% \begin{minipage}[b]{0.45\linewidth}
|
|
% \centering
|
|
% \begin{equation*}
|
|
% \mathcal{B}=\comprehension{X_{i,j}\cdot X_{i,j'}}{i \in [\ell], j\neq j' \in [~\abs{\block_i}~]}
|
|
% \end{equation*}
|
|
% \end{minipage}%
|
|
% \hspace{13mm}
|
|
% &
|
|
% \begin{minipage}[b]{0.45\linewidth}
|
|
% \centering
|
|
% \begin{equation*}
|
|
% \mathcal{T}=\comprehension{X_{i,j}^2-X_{i,j}}{i \in [\ell], j \in [~\abs{\block_i}~]}
|
|
% \end{equation*}
|
|
% \end{minipage}
|
|
% \\
|
|
%\end{tabular}
|
|
%}
|
|
%\end{Definition}
|
|
%%
|
|
\begin{Definition}[Reduced \bi Polynomials]\label{def:reduced-bi-poly}
|
|
Let $\poly(\vct{X})$ be a \bi-lineage polynomial.
|
|
The reduced form $\rpoly(\vct{X})$ of $\poly(\vct{X})$ is the same as \Cref{def:reduced-poly} with the added constraint that all monomials with variables $X_{\block, i}, X_{\block, j}, i\neq j$ from the same block $\block$ are omitted.
|
|
|
|
%: $\rpoly(\vct{X}) = \poly(\vct{X}) \mod \inparen{\mathcal{T} \cup \mathcal{B}}$
|
|
\end{Definition}
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%
|
|
|
|
Consider a $\abbrBIDB$ polynomial $\poly\inparen{\vct{X}} = X_{1, 1}X_{1, 2} + X_{1, 2}X_{2, 1}^2$. Then by \Cref{def:reduced-bi-poly}, we have that $\rpoly\inparen{\vct{X}} = X_{1, 2}X_{2, 1}$. Next, we show why the reduced form is useful for our purposes.
|
|
%, (recall the constraint on tuples from the same block being disjoint in a \bi).% any monomial containing more than one tuple from a block has $0$ probability and can be ignored).
|
|
%
|
|
%For the special case of \tis, the second step is not necessary since every block contains a single tuple.
|
|
%Alternatively, one can think of $\rpoly$ as the \abbrSMB of $\poly(\vct{X})$ when the product operator is idempotent.
|
|
%
|
|
% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
% \begin{Definition}[$\rpoly(\vct{X})$] \label{def:qtilde}
|
|
% Define $\rpoly(X_1,\ldots, X_\numvar)$ as the reduced version of $\poly(X_1,\ldots, X_\numvar)$, of the form
|
|
% $\rpoly(X_1,\ldots, X_\numvar) = $
|
|
|
|
% \[\poly(X_1,\ldots, X_\numvar) \mod X_1^2-X_1\cdots\mod X_\numvar^2 - X_\numvar.\]
|
|
% \end{Definition}
|
|
% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%%Removing this example to save space
|
|
\iffalse
|
|
\begin{Example}\label{example:qtilde}
|
|
Consider $\poly(X, Y) = (X + Y)(X + Y)$ where $X$ and $Y$ are from different blocks. The expanded derivation for $\rpoly(X, Y)$ is
|
|
\begin{align*}
|
|
(&X^2 + 2XY + Y^2 \mod X^2 - X) \mod Y^2 - Y\\
|
|
= ~&X + 2XY + Y^2 \mod Y^2 - Y\\
|
|
= ~& X + 2XY + Y
|
|
\end{align*}
|
|
\end{Example}
|
|
\fi
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%
|
|
% Intuitively, $\rpoly(\textbf{X})$ is the \abbrSMB form of $\poly(\textbf{X})$ such that if any $X_j$ term has an exponent $e > 1$, it is reduced to $1$, i.e. $X_j^e\mapsto X_j$ for any $e > 1$.
|
|
%
|
|
%When considering $\bi$ input, it becomes necessary to redefine $\rpoly(\vct{X})$.
|
|
%
|
|
%\noindent The usefulness of this will reduction become clear in \Cref{lem:exp-poly-rpoly}.
|
|
%
|
|
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%NEEDS to be moved to the appendix
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%\begin{Definition}[Valid Worlds]
|
|
%For probability distribution $\pd$, % and its corresponding probability mass function $\probOf$,
|
|
%the set of valid worlds $\valworlds$ consists of all the worlds with probability value greater than $0$; i.e., for random world variable vector $\vct{W}$
|
|
%\[
|
|
%\valworlds = \comprehension{\vct{w}}{\probOf[\vct{W} = \vct{w}] > 0}
|
|
%\]
|
|
%\end{Definition}
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
%END move to appendix
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
|
|
%We state additional equivalences between $\poly(\vct{X})$ and $\rpoly(\vct{X})$ in \Cref{app:subsec-pre-poly-rpoly} and \Cref{app:subsec-prop-q-qtilde}.
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
|
|
%Define all variables $X_i$ in $\poly$ to be independent.
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
\begin{Lemma}\label{lem:exp-poly-rpoly}
|
|
Let $\pdb$ be a \abbrBIDB over $\numvar$ input tuples such that the probability distribution $\pdassign$ over $\vct{\randWorld}^\numvar$ (the all worlds set) is induced by the probability vector $\probAllTup = (\prob_1, \ldots, \prob_\numvar)$. As in \Cref{lem:tidb-reduce-poly} for \abbrTIDB, any \abbrBIDB-lineage polynomial $\poly(\vct{X})$ based on $\pdb$ and query $\query$ we have:
|
|
% The expectation over possible worlds in $\poly(\vct{X})$ is equal to $\rpoly(\prob_1,\ldots, \prob_\numvar)$.
|
|
\begin{equation*}
|
|
\expct_{\vct{W}\sim \pd}\pbox{\poly(\vct{W})} = \rpoly(\probAllTup).
|
|
\end{equation*}
|
|
\end{Lemma}
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
By \Cref{lem:exp-poly-rpoly} and linearity of expectation, the following corollary results.
|
|
%Note that in the preceding lemma, we have assigned $\vct{p}$
|
|
%%(introduced in \Cref{subsec:def-data})
|
|
%to the variables $\vct{X}$. Intuitively, \Cref{lem:exp-poly-rpoly} states that when we replace each variable $X_i$ with its probability $\prob_i$ in the reduced form of a \bi-lineage polynomial and evaluate the resulting expression in $\mathbb{R}$, then the result is the expectation of the polynomial.
|
|
|
|
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
\begin{Corollary}\label{cor:expct-sop}
|
|
If $\poly$ is a \bi-lineage polynomial already in \abbrSMB, then the expectation of $\poly$, i.e., $\expct\pbox{\poly} = \rpoly\left(\prob_1,\ldots, \prob_\numvar\right)$ can be computed in $\bigO{\size\inparen{\poly}}$, where $\size\inparen{\poly}$ (\Cref{def:size-depth}) is proportional to the total number of multiplication/addition operators in $\poly$.
|
|
\end{Corollary}
|
|
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|
|
|
|
%%% Local Variables:
|
|
%%% mode: latex
|
|
%%% TeX-master: "main"
|
|
%%% End:
|