%root: main.tex %!TEX root=./main.tex \section{$1 \pm \epsilon$ Approximation Algorithm}\label{sec:algo} In~\Cref{sec:hard}, we showed that computing the expected multiplicity of a compressed representation of a bag polynomial for \ti (even just based on project-join queries) is unlikely to be possible in linear time (\Cref{thm:mult-p-hard-result}), even if all tuples have the same probability (\Cref{th:single-p-hard}). Given this, we now design an approximation algorithm for our problem that runs in {\em linear time}. The folowing approximation algorithm applies to \bi, though our bounds are more meaningful for a non-trivial subclass of \bis that contains both \tis, as well as the PDBench benchmark~\cite{pdbench}. %it is then desirable to have an algorithm to approximate the multiplicity in linear time, which is what we describe next. \subsection{Preliminaries and some more notation} We now introduce useful definitions and notation related to polynomials. We use the following polynomial as an example: \begin{equation} \label{eq:poly-eg} \poly(X, Y) = 2X^2 + 3XY - 2Y^2. \end{equation} \begin{Definition}[Variables in a monomial]\label{def:vars} Given a monomial $v$, we use $\var(v)$ to denote the set of variables in $v$. \end{Definition} \noindent For example the monomial $XY$ has $\var(XY)=\inset{X,Y}$. \revision{ \begin{Definition}[Pure Expansion] The pure expansion of a polynomial $\poly$ is formed by computing all product of sums occurring in $\poly$, without combining like monomials. The pure expansion of $\poly$ generalizes \Cref{def:smb} by allowing monomials $m_i = m_j$ for $i \neq j$. \end{Definition} } \begin{Definition}[Expanded \revision{\circuit}]\label{def:expand-circuit} %\revision{$\expansion{\circuit}$} is the reduced pure expansion of $\revision{\circuit}$. The logical view of \revision{$\expansion{\circuit}$} is a list of tuples $(\monom, \coef)$, where $\monom$ is a set of variables and $\coef$ is in $\reals$. \revision{$\expansion{\circuit}$} has the following recursive definition ($\circ$ is list concatenation). $\expansion{\circuit} = \begin{cases} \expansion{\circuit_\linput} \circ \expansion{\circuit_\rinput} &\textbf{ if }\revision{\circuit.\type = \circplus}\\ \left\{(\monom_\linput \cup \monom_\rinput, \coef_\linput \cdot \coef_\rinput) ~|~(\monom_\linput, \coef_\linput) \in \expansion{\circuit_\linput}, (\monom_\rinput, \coef_\rinput) \in \expansion{\circuit_\rinput}\right\} &\textbf{ if }\revision{\circuit.\type = \circmult}\\ \elist{(\emptyset, \revision{\circuit.\val})} &\textbf{ if }\revision{\circuit}.\type = \tnum\\ \elist{(\{\revision{\circuit}.\val\}, 1)} &\textbf{ if }\revision{\circuit}.\type = \var.\\ \end{cases} $ \end{Definition} \revision{ Note that similar in spirit to \Cref{def:reduced-bi-poly}, $\expansion{\circuit}$ reduces all variable exponents $e > 1$ to $e = 1$. } In the following, we abuse notation and write $\monom$ to denote the monomial obtained as the products of the variables in the set. \begin{Example}\label{example:expr-tree-T} Consider the factorized representation $(X+ 2Y)(2X - Y)$ of the polynomial in~\Cref{eq:poly-eg}. Its circuit $\circuit$ is illustrated in \cref{fig:circuit}. The pure expansion of the product is $2X^2 - XY + 4XY - 2Y^2$ and the $\expansion{\circuit}$ is $[(X, 2), (XY, -1), (XY, 4), (Y, -2)]$. \end{Example} $\expansion{\circuit}$ effectively\footnote{The minor difference here is that $\expansion{\circuit}$ encodes the \emph{reduced} form over the SOP expansion of the compressed representation, as opposed to the \abbrSMB representation} encodes the \emph{reduced} form of $\polyf\inparen{\circuit}$, decoupling each monomial into a set of variables $\monom$ and a real coefficient $\coef$. However, unlike the constraint on the input to compute $\rpoly$, the input circuit $\circuit$ does not need to be in \abbrSMB/SOP form. \begin{Definition}[Positive \circuit]\label{def:positive-circuit} For any circuit $\circuit$, the corresponding {\em positive circuit}, denoted $\abs{\circuit}$, is obtained from $\circuit$ as follows. For each leaf node $\ell$ of $\circuit$ where $\ell.\type$ is $\tnum$, update $\ell.\vari{value}$ to $|\ell.\vari{value}|$. \end{Definition} Using the same factorization from \Cref{example:expr-tree-T}, $\polyf(\abs{\circuit}) = (X + 2Y)(2X + Y) = 2X^2 +XY +4XY + 2Y^2 = 2X^2 + 5XY + 2Y^2$. Note that this \textit{is not} the same as the polynomial from~\Cref{eq:poly-eg}. \begin{Definition}[Evaluation]\label{def:exp-poly-eval} Given an expression tree $\circuit$ and a valuation $\vct{a} \in \mathbb{R}^\numvar$, we define the evaluation of $\circuit$ on $\vct{a}$ as $\circuit(\vct{a}) = \polyf(\circuit)(\vct{a})$. \end{Definition} \begin{Definition}[\size($\cdot$)] The function \size~ takes a circuit $\circuit$ as input and outputs the number of gates (nodes) in \circuit. \end{Definition} \begin{Definition}[\depth($\cdot$)] The function \depth~ has circuit $\circuit$ as input and outputs the number of levels in \circuit. \end{Definition} \begin{Definition}[$\degree(\cdot)$] \revision{ $\degree(\circuit)$ is defined recursively as follows: \[\degree(\circuit)= \begin{cases} \max(\degree(\circuit_\linput),\degree(\circuit_\rinput)) & \text{ if }\circuit.type=+\\ \degree(\circuit_\linput) + \degree(\circuit_\rinput)+1 &\text{ if }\circuit.type=\times\\ 0 & \text{otherwise}. \end{cases} \] } %If $\circuit$ has no $+$ or $\times$ gate, then $\deg(\circuit)=0$. Otherwise if %The function $\degree(\cdot)$ takes a circuit \circuit as input and outputs the degree of $\polyf(\abs{\circuit})$. \end{Definition} \revision{Note that the degree of $\polyf(\abs{\circuit})$ is always upper bounded by $\deg(\circuit)$ and the latter can be strictly larger (e.g. consider the case when $\circuit$ multiplies two copies of the constant $1$-- here we have $\deg(\circuit)=1$ but degree of $\polyf(\abs{\circuit})$ is $0$).} \begin{Definition}[Subcircuit] A subcircuit of a circuit $\circuit$ is a circuit \subcircuit such that \subcircuit is a DAG \textit{subgraph} of the DAG representing \circuit. The sink of \subcircuit has exactly one gate \gate. \end{Definition} Finally, we will need the following notation for the complexity of multiplying large integers: \begin{Definition}[$\multc{\cdot}{\cdot}$] In a RAM model of word size of $W$-bits, $\multc{M}{W}$ denotes the complexity of multiplying two integers represented with $M$-bits. (We will assume that for input of size $N$, $W=O(\log{N})$. \end{Definition} We note that when doing arithmetic operations on the RAM model for input of size $N$, we have that $\multc{O(\log{N})}{O(\log{N})}=O(1)$. More generally we have $\multc{N}{O(\log{N})}=O(N\log{N}\log\log{N})$. \subsection{Our main result} In the subsequent subsections we will prove the following theorem. \begin{Theorem}\label{lem:approx-alg} Let \circuit be a circuit for a UCQ over \bi and define $\poly(\vct{X})=\polyf(\circuit)$ and let $k=\degree(\circuit)$. Then an estimate $\mathcal{E}$ of $\rpoly(\prob_1,\ldots, \prob_\numvar)$ can be computed in time {\small \[O\left(\left(\size(\circuit) + \frac{\log{\frac{1}{\conf}}\cdot \abs{\circuit}^2(1,\ldots, 1)\cdot k\cdot \log{k} \cdot \depth(\circuit))}{\inparen{\error'}^2\cdot\rpoly^2(\prob_1,\ldots, \prob_\numvar)}\right)\cdot\multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log\left(\size(\circuit)\right)}\right)\] } such that \begin{equation} \label{eq:approx-algo-bound} \probOf\left(\left|\mathcal{E} - \rpoly(\prob_1,\dots,\prob_\numvar)\right|> \error' \cdot \rpoly(\prob_1,\dots,\prob_\numvar)\right) \leq \conf. \end{equation} \end{Theorem} \noindent The proof of~\Cref{lem:approx-alg} (which relies on \Cref{lem:one-pass} and \Cref{lem:sample}) can be found in~\Cref{sec:proof-lem-approx-alg}. The proofs for the referenced lemmas are also found in \Cref{sec:proof-one-pass} and \Cref{sec:proof-sample-monom}. To get linear runtime results from~\Cref{lem:approx-alg}, we will need to define another parameter modeling the (weighted) number of monomials in $\expansion{\circuit}$ to be `canceled' when it is modded with $\mathcal{B}$ (\Cref{def:mod-set-polys}). \begin{Definition}[Parameter $\gamma$]\label{def:param-gamma} Given an expression tree $\circuit$, define \[\gamma(\circuit)=\frac{\sum_{(\monom, \coef)\in \expansion{\circuit}} \abs{\coef}\cdot \indicator{\monom\mod{\mathcal{B}}\equiv 0}}{\abs{\circuit}(1,\ldots, 1)}\] \end{Definition} \noindent We next present a few corollaries of~\Cref{lem:approx-alg}. \begin{Corollary} \label{cor:approx-algo-const-p} Let $\poly(\vct{X})$ be as in~\Cref{lem:approx-alg} and let $\gamma=\gamma(\circuit)$. Further let it be the case that $\prob_i\ge \prob_0$ for all $i\in[\numvar]$. Then an estimate $\mathcal{E}$ of $\rpoly(\prob_1,\ldots, \prob_\numvar)$ satisfying~\Cref{eq:approx-algo-bound} can be computed in time \[O\left(\left(\size(\circuit) + \frac{\log{\frac{1}{\conf}}\cdot k\cdot \log{k} \cdot \depth(\circuit))}{\inparen{\error'}^2\cdot(1-\gamma)^2\cdot \prob_0^{2k}}\right)\cdot\multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log\left(\size(\circuit)\right)}\right)\] In particular, if $\prob_0>0$ and $\gamma<1$ are absolute constants then the above runtime simplifies to $O_k\left(\left(\frac 1{\inparen{\error'}^2}\cdot\size(\circuit)\cdot \log{\frac{1}{\conf}}\right)\cdot\multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log\left(\size(\circuit)\right)}\right)$. \end{Corollary} The proof for~\Cref{cor:approx-algo-const-p} can be seen in~\Cref{sec:proofs-approx-alg}. The restriction on $\gamma$ is satisfied by any \ti (where $\gamma=0$) as well as for all three queries of the PDBench \bi benchmark (\Cref{app:subsec:experiment} shows experimentally that $\gamma$ is negligible in practice for these queries). We also observe that (i) tuple presence is independent across blocks, so the corresponding probabilities (and hence $\prob_0$) are independent of the number of blocks, and (ii) \bis model uncertain attributes, so block size (and hence $\gamma$) is a function of the ``messiness'' of a dataset, rather than its size. Thus, we expect the corollary to hold in general. Finally, we address the $\multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log\left(\size(\circuit)\right)}$ term in the runtime. In Appendix\revision{Fill in ref later on}, we show the following: \begin{Lemma} \label{lem:val-ub} For any circuit $\circuit$ with $\degree(\circuit)=k$, we have \[\abs{\circuit}(1,\ldots, 1)\le 2^{2^k\cdot \size(\circuit)}.\] Further, under either of the following conditions: \begin{enumerate} \item $\circuit$ is a tree, \item $\circuit$ encodes the run of the algorithm in~\cite{DBLP:conf/pods/KhamisNR16} on an FAQ query, \end{enumerate} we have \[\abs{\circuit}(1,\ldots, 1)\le \size(\circuit)^{O(k)}.\] \end{Lemma} Note that the above implies that with the assumption $\prob_0>0$ and $\gamma<1$ are absolute constants from \Cref{cor:approx-algo-const-p}, then the runtime there simplies to $O_k\left(\frac 1{\inparen{\error'}^2}\cdot\size(\circuit)^2\cdot \log{\frac{1}{\conf}}\right)$ for general circuits $\circuit$ and to $O_k\left(\frac 1{\inparen{\error'}^2}\cdot\size(\circuit)\cdot \log{\frac{1}{\conf}}\right)$ for the case when $\circuit$ satisfies the special conditions in~\Cref{lem:val-ub}. In~\Cref{app:proof-lem-val-ub} we argue that these conditions are very general and encompass many interesting scenarios. \subsection{Approximating $\rpoly$} The algorithm to prove~\Cref{lem:approx-alg} follows from the following observation. Given a query polynomial $\poly(\vct{X})=\polyf(\circuit)$ for circuit \circuit over $\bi$, we can exactly represent $\rpoly(\vct{X})$ as follows: \begin{equation} \label{eq:tilde-Q-bi} \rpoly\inparen{X_1,\dots,X_\numvar}=\hspace*{-1mm}\sum_{(\monom,\coef)\in \expansion{\circuit}} \hspace*{-2mm} \indicator{\monom\mod{\mathcal{B}}\not\equiv 0}\cdot \coef\cdot\hspace*{-2mm}\prod_{X_i\in \var\inparen{\monom}}\hspace*{-2mm} X_i \end{equation} Given the above, the algorithm is a sampling based algorithm for the above sum: we sample $(\monom,\coef)\in \expansion{\circuit}$ with probability proportional\footnote{We could have also uniformly sampled from $\expansion{\circuit}$ but this gives better parameters.} to $\abs{\coef}$ and compute $Y=\indicator{\monom\mod{\mathcal{B}}\not\equiv 0}\cdot \prod_{X_i\in \var\inparen{\monom}} p_i$. Taking $\numsamp$ samples and computing the average of $Y$ gives us our final estimate. The number of samples is computed by (see \Cref{app:subsec-th-mon-samp}): \begin{equation*} 2\exp{\left(-\frac{\samplesize\error^2}{2}\right)}\leq \conf \implies\samplesize \geq \frac{2\log{\frac{2}{\conf}}}{\error^2}. \end{equation*} To summarize, \approxq modifies \circuit with a call to \onepass. It then samples from \circuit, $\numsamp$ times and uses that information to approximate $\rpoly$. \begin{algorithm}[t] \caption{$\approxq(\circuit, \vct{p}, \conf, \error)$} \label{alg:mon-sam} \begin{algorithmic}[1] \Require \circuit: Circuit \Require $\vct{p} = (\prob_1,\ldots, \prob_\numvar)$ $\in [0, 1]^N$ \Require $\conf$ $\in [0, 1]$ \Require $\error$ $\in [0, 1]$ \Ensure \vari{acc} $\in \mathbb{R}$ \State $\accum \gets 0$\label{alg:mon-sam-global1} \State $\numsamp \gets \ceil{\frac{2 \log{\frac{2}{\conf}}}{\error^2}}$\label{alg:mon-sam-global2} \State $(\circuit_\vari{mod}, \vari{size}) \gets $ \onepass($\circuit$)\label{alg:mon-sam-onepass}\Comment{$\onepass$ is \Cref{alg:one-pass-iter}} \For{$\vari{i} \in 1 \text{ to }\numsamp$}\label{alg:sampling-loop}\Comment{Perform the required number of samples} \State $(\vari{M}, \vari{sgn}_\vari{i}) \gets $ \sampmon($\circuit_\vari{mod}$)\label{alg:mon-sam-sample} \State\Comment{\sampmon \; is \Cref{alg:sample}} \If{$\vari{M}$ has at most one variable from each block}\label{alg:check-duplicate-block} \State $\vari{Y}_\vari{i} \gets \prod_{X_j\in\var\inparen{\vari{M}}}p_j$\label{alg:mon-sam-assign1} \State $\vari{Y}_\vari{i} \gets \vari{Y}_\vari{i} \times\; \vari{sgn}_\vari{i}$\label{alg:mon-sam-product} \State $\accum \gets \accum + \vari{Y}_\vari{i}$\Comment{Store the sum over all samples}\label{alg:mon-sam-add} \EndIf \EndFor \State $\vari{acc} \gets \vari{acc} \times \frac{\vari{size}}{\numsamp}$\label{alg:mon-sam-global3} \State \Return \vari{acc} \end{algorithmic} \end{algorithm} \subsubsection{Correctness} In order to prove~\Cref{lem:approx-alg}, we will need to argue the correctness of~\Cref{alg:mon-sam}. Before we formally do that, we first state the lemmas that summarize the relevant properties of $\onepass$ and $\sampmon$, the auxiliary algorithms on which \Cref{alg:mon-sam} relies. \begin{Lemma}\label{lem:one-pass} The $\onepass$ function completes in time: $$O\left(\size(\circuit) \cdot \multc{\log\left(\abs{\circuit(1\ldots, 1)}\right)}{\log{\size(\circuit}}\right)$$ $\onepass$ guarantees two post-conditions: First, for each subcircuit $\vari{S}$ of $\circuit$, we have that $\vari{S}.\vari{partial}$ is set to $\abs{\vari{S}}(1,\ldots, 1)$. Second, when $\vari{S}.\type = \circplus$, \subcircuit.\lwght $= \frac{\abs{\subcircuit_\linput}(1,\ldots, 1)}{\abs{\subcircuit}(1,\ldots, 1)}$ and likewise for \subcircuit.\rwght. \end{Lemma} To prove correctness of~\Cref{alg:mon-sam}, we only use the following fact that follows from the above lemma: for the modified circuit ($\circuit_{\vari{mod}}$), $\circuit_{\vari{mod}}.\vari{partial}=\abs{\circuit}(1,\dots,1)$. \begin{Lemma}\label{lem:sample} The function $\sampmon$ completes in time $$O(\log{k} \cdot k \cdot \depth(\circuit)\cdot\multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log{\size(\circuit)}})$$ where $k = \degree(\circuit)$. The function returns every $\left(\monom, sign(\coef)\right)$ for $(\monom, \coef)\in \expansion{\circuit}$ with probability $\frac{|\coef|}{\abs{\circuit}(1,\ldots, 1)}$. \end{Lemma} With the above two lemmas, we are ready to argue the following result (proof in~\Cref{sec:proofs-approx-alg}): \begin{Theorem}\label{lem:mon-samp} For any $\circuit$ with $\degree(poly(|\circuit|)) = k$, algorithm \ref{alg:mon-sam} outputs an estimate $\vari{acc}$ of $\rpoly(\prob_1,\ldots, \prob_\numvar)$ such that \[\probOf\left(\left|\vari{acc} - \rpoly(\prob_1,\ldots, \prob_\numvar)\right|> \error \cdot \abs{\circuit}(1,\ldots, 1)\right) \leq \conf,\] in $O\left(\left(\size(\circuit)+\frac{\log{\frac{1}{\conf}}}{\error^2} \cdot k \cdot\log{k} \cdot \depth(\circuit)\right)\cdot \multc{\log\left(\abs{\circuit}(1,\ldots, 1)\right)}{\log{\size(\circuit)}}\right)$ time. \end{Theorem} \subsection{\onepass\ Algorithm} \label{sec:onepass} The evaluation of $\abs{\circuit}(1,\ldots, 1)$ can be defined recursively, as follows (where $\circuit_\linput$ and $\circuit_\rinput$ are the `left' and `right' inputs of $\circuit$ if they exist): {\small \begin{align} \label{eq:T-all-ones} \abs{\circuit}(1,\ldots, 1) = \begin{cases} \abs{\circuit_\linput}(1,\ldots, 1) \cdot \abs{\circuit_\rinput}(1,\ldots, 1) &\textbf{if }\circuit.\type = \revision{\circmult}\\ \abs{\circuit_\linput}(1,\ldots, 1) + \abs{\circuit_\rinput}(1,\ldots, 1) &\textbf{if }\circuit.\type = \revision{\circplus} \\ |\circuit.\val| &\textbf{if }\circuit.\type = \tnum\\ 1 &\textbf{if }\circuit.\type = \var. \end{cases} \end{align} } It turns out that for proof of~\Cref{lem:sample}, we need to argue that when $\circuit.\type = +$, we indeed have \begin{align} \label{eq:T-weights} \circuit.\lwght &\gets \frac{\abs{\circuit_\linput}(1,\ldots, 1)}{\abs{\circuit_\linput}(1,\ldots, 1) + \abs{\circuit_\rinput}(1,\ldots, 1)};\\ \circuit.\rwght &\gets \frac{\abs{\circuit_\rinput}(1,\ldots, 1)}{\abs{\circuit_\linput}(1,\ldots, 1)+ \abs{\circuit_\rinput}(1,\ldots, 1)} \end{align} \noindent \onepass\ (Algorithm ~\ref{alg:one-pass-iter} in \Cref{sec:proofs-approx-alg}) iteratively visits each gate one time according to the topological ordering of \circuit annotating the \lwght, \rwght, and \prt variables of each node according to the definitions above. Lemma~\ref{lem:one-pass} is proved in~\Cref{sec:proofs-approx-alg}. \subsection{\sampmon\ Algorithm} \label{sec:samplemonomial} A naive (slow) implementation of \sampmon\ would first compute $\expansion{\circuit}$ and then sample from it. Instead, \Cref{alg:sample} selects a monomial from $\expansion{\circuit}$ by top-down traversal. For a parent $+$ gate, the input to be visited is sampled from the weighted distribution precomputed by \onepass. When a parent $\times$ node is visited, both inputs are visited. The algorithm computes two properties: the set of all variable leaf nodes visited, and the product of signs of visited coefficient leaf nodes. % We will assume the TreeSet data structure to maintain sets with logarithmic time insertion and linear time traversal of its elements. % $\sampmon$ is given in \Cref{alg:sample}, and a proof of its correctness (via \Cref{lem:sample}) is provided in \Cref{sec:proofs-approx-alg}. \begin{algorithm}[t] \caption{\sampmon(\circuit)} \label{alg:sample} \begin{algorithmic}[1] \revision{\Require \circuit: Circuit} \Ensure \vari{vars}: TreeSet \Ensure \vari{sgn} $\in \{-1, 1\}$ \Comment{\Cref{alg:one-pass-iter} should have been run before this one} % algorithm ~\ref{alg:sample}} \State $\vari{vars} \gets \emptyset$ \label{alg:sample-global1} \If{$\circuit.\type = +$}\Comment{Sample at every $+$ node} \State $\circuit_{\vari{samp}} \gets$ Sample from left input ($\circuit_{\linput}$) and right input ($\circuit_{\rinput}$) w.p. $\circuit.\vari{Lweight}$ and $\circuit.\vari{Rweight}$. \label{alg:sample-plus-bsamp} \Comment{Each call to \sampmon uses fresh randomness} \State $(\vari{v}, \vari{s}) \gets \sampmon(\circuit_{\vari{samp}})$\label{alg:sample-plus-traversal} \State $\Return ~(\vari{v}, \vari{s})$ \ElsIf{$\circuit.\type = \times$}\Comment{Multiply the sampled values of all inputs} \State $\vari{sgn} \gets 1$\label{alg:sample-global2} \For {$input$ in $\circuit.\vari{input}$}\label{alg:sample-times-for-loop} \State $(\vari{v}, \vari{s}) \gets \sampmon(input)$ \State $\vari{vars} \gets \vari{vars} \cup \{\vari{v}\}$\label{alg:sample-times-union} \State $\vari{sgn} \gets \vari{sgn} \times \vari{s}$\label{alg:sample-times-product} \EndFor \State $\Return ~(\vari{vars}, \vari{sgn})$ \ElsIf{$\circuit.\type = numeric$}\Comment{The leaf is a coefficient} %\State $\vari{sgn} \gets \vari{sgn} \times sign(\circuit.\val)$ \State $\Return ~\left(\{\}, sign(\circuit.\val)\right)$\label{alg:sample-num-return} \ElsIf{$\circuit.\type = var$} %\State $\vari{vars} \gets \vari{vars} \; \cup \; \{\;\circuit.\val\;\}\label{alg:sample-var-union}$\Comment{Add the variable to the set} \State $\Return~\left(\{\circuit.\val\}, 1\right) $\label{alg:sample-var-return} \EndIf \end{algorithmic} \end{algorithm} % \subsection{Experimental results} % \label{sec:experiments} % We conducted an experiment running modified TPCH queries over uncertain data generated by pdbench~\cite{pdbench}, both of which (data and queries) represent what is typically encountered in practice. Queries were run two times, once filtering $\bi$ cancellations, and then second not filtering the cancellations. The purpose of this was to determine an indication for how many $\bi$ cancellations occur in practice. Details and results can be found in~. %\AR{Experimental stuff about \bi should go in here} %%%%%%%%%%%%%%%%%%%%%%% %%% Local Variables: %%% mode: latex %%% TeX-master: "main" %%% End: