Done with pass on App D

appendix.tex

@@ -25,7 +25,8 @@
 \subsection{Representing Polynomials with Circuits}\label{app:subsec-rep-poly-lin-circ}
 \subsubsection{Circuits for query plans}
 \label{sec:circuits-formal}
-We now formalize circuits and the construction of circuits for SPJU queries.
+\AR{Since this comment is not showing up below, I do not follow why the last sentence of this para is true.}
+We now formalize circuits and the construction of circuits for $\raPlus$ queries.
 As mentioned earlier, we represent lineage polynomials as arithmetic circuits over $\mathbb N$-valued variables with $+$, $\times$.
 A circuit for query $Q$ and \abbrNXPDB $\pxdb$ is a directed acyclic graph $\tuple{V_{Q,\pxdb}, E_{Q,\pxdb}, \phi_{Q,\pxdb}, \ell_{Q,\pxdb}}$ with vertices $V_{Q,\pxdb}$ and directed edges $E_{Q,\pxdb} \subset {V_{Q,\pxdb}}^2$.
 The sink function $\phi_{Q,\pxdb} : \udom^n \rightarrow V_{Q,\pxdb}$ is a partial function that maps the tuples of the $n$-ary\AR{In the main paper we have used $n$ to denote the number of input tuples so we need to use some other notation $n$ but since I do not know where all this change will need to be propagated so am not changing it for now.} relation $Q(\pxdb)$ to vertices.
@@ -76,17 +77,17 @@ We define the circuit for a $\raPlus$ query $\query$ recursively by cases as fol
   \If{$\query$ is $R$} \Comment{\textbf{Case 1}: $\query$ is a relation atom}
     \For{$t \in \dbbase.R$}
       \State $V \leftarrow V \cup \{v_t\}$; $\ell \leftarrow \ell \cup \{(v_t, R(t))\}$  \Comment{Allocate a fresh node $v_t$}
-      \State $\phi(t) = v_t$ 
+      \State $\phi(t) \gets v_t$ 
     \EndFor
   \ElsIf{$\query$ is $\sigma_\theta(\query')$} \Comment{\textbf{Case 2}: $\query$ is a Selection}
-    \State $\tuple{V, E, \phi', \ell} = \abbrStepOne(\query', \dbbase, V, E, \ell)$
+    \State $\tuple{V, E, \phi', \ell} \gets \abbrStepOne(\query', \dbbase, V, E, \ell)$
     \For{$t \in \domain(\phi')$}
       \State \textbf{if }$\theta(t)$
-              \textbf{ then } $\phi(t) = \phi'(t)$
+              \textbf{ then } $\phi(t) \gets \phi'(t)$
-              \textbf{ else } $\phi(t) = v_0$
+              \textbf{ else } $\phi(t) \gets v_0$
     \EndFor
   \ElsIf{$\query$ is $\pi_{\vec{A}}(\query')$} \Comment{\textbf{Case 3}: $\query$ is a Projection}
-    \State $\tuple{V, E, \phi', \ell} = \abbrStepOne(\query', \dbbase, V, E, \ell)$
+    \State $\tuple{V, E, \phi', \ell} \gets \abbrStepOne(\query', \dbbase, V, E, \ell)$
     \For{$t \in \pi_{\vec{A}}(\query'(\dbbase))$}
       \State $V \leftarrow V \cup \{v_t\}$; $\ell \leftarrow \ell \cup \{(v_t, +)\}$\Comment{Allocate a fresh node $v_t$}
       \State $\phi(t) \leftarrow v_t$
@@ -94,26 +95,26 @@ We define the circuit for a $\raPlus$ query $\query$ recursively by cases as fol
     \For{$t \in \query'(\dbbase)$}
       \State $E \leftarrow E \cup \{(\phi'(t), \phi(\pi_{\vec{A}}t))\}$
     \EndFor
-    \State Correct nodes with in-degrees $>2$ by appending an equivalent fan-in tree instead
+    \State Correct nodes with in-degrees $>2$ by appending an equivalent fan-in two tree instead
   \ElsIf{$\query$ is $\query_1 \cup \query_2$} \Comment{\textbf{Case 4}: $\query$ is a Bag Union}
-    \State $\tuple{V, E, \phi_1, \ell} = \abbrStepOne(\query_1, \dbbase, V, E, \ell)$
+    \State $\tuple{V, E, \phi_1, \ell} \gets \abbrStepOne(\query_1, \dbbase, V, E, \ell)$
-    \State $\tuple{V, E, \phi_2, \ell} = \abbrStepOne(\query_2, \dbbase, V, E, \ell)$
+    \State $\tuple{V, E, \phi_2, \ell} \gets \abbrStepOne(\query_2, \dbbase, V, E, \ell)$
-    \State $\phi = \phi_1 \cup \phi_2$
+    \State $\phi \gets \phi_1 \cup \phi_2$
     \For{$t \in \domain(\phi_1) \cap \domain(\phi_2)$}
       \State $V \leftarrow V \cup \{v_t\}$; $\ell \leftarrow \ell \cup \{(v_t, +)\}$ \Comment{Allocate a fresh node $v_t$}
-      \State $\phi(t) = v_t$
+      \State $\phi(t) \gets v_t$
       \State $E \leftarrow E \cup \{(\phi_1(t), v_t), (\phi_2(t), v_t)\}$
     \EndFor
-  \ElsIf{$\query$ is $\query_1 \bowtie \ldots \bowtie \query_n$} \Comment{\textbf{Case 5}: $\query$ is a n-ary Join}
+  \ElsIf{$\query$ is $\query_1 \bowtie \ldots \bowtie \query_m$} \Comment{\textbf{Case 5}: $\query$ is a $m$-ary Join}
-    \For{$i \in [n]$}
+    \For{$i \in [m]$}
-      \State $\tuple{V, E, \phi_i, \ell} = \abbrStepOne(\query_i, \dbbase, V, E, \ell)$
+      \State $\tuple{V, E, \phi_i, \ell} \gets \abbrStepOne(\query_i, \dbbase, V, E, \ell)$
     \EndFor
-    \For{$t \in \domain(\phi_1) \bowtie \ldots \bowtie \domain(\phi_k)$}
+    \For{$t \in \domain(\phi_1) \bowtie \ldots \bowtie \domain(\phi_m)$}
       \State $V \leftarrow V \cup \{v_t\}$; $\ell \leftarrow \ell \cup \{(v_t, \times)\}$ \Comment{Allocate a fresh node $v_t$}
-      \State $\phi(t) = v_t$
+      \State $\phi(t) \gets v_t$
       \State $E \leftarrow E \cup \comprehension{(\phi_i(\pi_{sch(\query_i(\dbbase))}(t)), v_t)}{i \in [n]}$
     \EndFor
-    \State Correct nodes with in-degrees $>2$ by appending an equivalent fan-in tree instead
+    \State Correct nodes with in-degrees $>2$ by appending an equivalent fan-in two tree instead
 
   \EndIf
 
@@ -179,12 +180,12 @@ There are $|{Q_1} \bowtie \ldots \bowtie {Q_k}|$ such vertices, so the corrected
 \subsubsection{Bounding circuit depth}
 \label{sec:circuit-depth}
 
-We first show that the depth of the circuit (\depth; \Cref{def:size-depth}) is bounded by the size of the query.  Denote by $|\query|$ the number of relational operators in query $\query$, which recall we assume as a constant.
+We first show that the depth of the circuit (\depth; \Cref{def:size-depth}) is bounded by the size of the query.  Denote by $|\query|$ the number of relational operators in query $\query$, which recall we assume is a constant.
 
 \begin{Proposition}[Circuit depth is bounded]
 \label{prop:circuit-depth}
 Let $\query$ be a relational query and $\dbbase$ be a \dbbaseName with $n$ tuples.  There exists a (lineage) circuit $\circuit^*$ encoding the lineage of all tuples $\tup \in \query(\dbbase)$ for which 
-$\depth(\circuit^*) \leq O(k|\query|\log(n))$
+$\depth(\circuit^*) \leq O(k|\query|\log(n))$.
 \end{Proposition}
 
 \begin{proof}
@@ -204,21 +205,21 @@ For the projection case, observe that the fan-in is bounded by $|\query'(\dbbase
 
 \begin{Lemma}\label{lem:circ-model-runtime}
 \label{lem:circuits-model-runtime}
-Given a \abbrNXPDB $\pxdb$ with \dbbaseName $\dbbase$, and query plan $Q$, the runtime of $Q$ over $\dbbase$ has the same or greater complexity as the size of the lineage of $Q(\pxdb)$.  That is, we have $\abs{V_{Q,\pxdb}} \leq (k-1)\qruntime{Q, \dbbase}+1$, where $k$ is the maximal degree of  any  polynomial in $Q(\pxdb)$.
+Given a \abbrNXPDB $\pxdb$ with \dbbaseName $\dbbase$, and an $\raPlus$ query  $Q$, the runtime of $Q$ over $\dbbase$ has the same or greater complexity as the size of the lineage of $Q(\pxdb)$.  That is, we have $\abs{V_{Q,\pxdb}} \leq k\qruntime{Q, \dbbase}+1$, where $k\ge 1$ is the maximal degree of  any  polynomial in $Q(\pxdb)$.
 \end{Lemma}
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 %\noindent The proof is shown in \Cref{app:subsec-lem-lin-vs-qplan}.
 
 %\subsection{Proof for \Cref{lem:circuits-model-runtime}}\label{app:subsec-lem-lin-vs-qplan}
 \begin{proof}
-We prove by induction that $\abs{V_{Q,\pxdb} - \{v_0\}} \leq (k-1)\qruntime{Q, \dbbase}$.  For clarity, we implicitly exclude $v_0$ in the proof below.
+We prove by induction that $\abs{V_{Q,\pxdb} \setminus \{v_0\}} \leq k\qruntime{Q, \dbbase}$.  For clarity, we implicitly exclude $v_0$ in the proof below.
 
-The base case is a base relation: $Q = R$ and is trivially true since $|V_{R,\pxdb}| = |D_\Omega.R|$.
+The base case is a base relation: $Q = R$ and is trivially true since $|V_{R,\pxdb}| = |\dbbase.R|=\qruntime{R, \dbbase}$ (note that here the degree $k=1$).
-For the inductive step, we assume that we have circuits for subplans $Q_1, \ldots, Q_n$ such that $|V_{Q_i,\pxdb}| \leq (k_i-1)\qruntime{Q_i,\dbbase}$ where $k_i$ is the degree of $Q_i$.
+For the inductive step, we assume that we have circuits for subqueries $Q_1, \ldots, Q_m$ such that $|V_{Q_i,\pxdb}| \leq k_i\qruntime{Q_i,\dbbase}$ where $k_i$ is the degree of $Q_i$.
 
 \caseheading{Selection}
 Assume that $Q = \sigma_\theta(Q_1)$.
-In the circuit for $Q$, $|V_{Q,\pxdb}| = |V_{Q_1,\dbbase}|$ vertices, so from the inductive assumption and $\qruntime{Q,\dbbase} = \qruntime{Q_1,\dbbase}$ by definition, we have $|V_{Q,\pxdb}| \leq (k-1) \qruntime{Q,\dbbase} $.
+In the circuit for $Q$, $|V_{Q,\pxdb}| = |V_{Q_1,\dbbase}|$ vertices, so from the inductive assumption and $\qruntime{Q,\dbbase} = \qruntime{Q_1,\dbbase}$ by definition, we have $|V_{Q,\pxdb}| \leq k \qruntime{Q,\dbbase} $.
 % \AH{Technically, $\kElem$ is the degree of $\poly_1$, but I guess this is a moot point since one can argue that $\kElem$ is also the degree of $\poly$.}
 % OK: Correct
 
@@ -231,9 +232,9 @@ The circuit for $Q$ has at most $|V_{Q_1,\pxdb}|+|{Q_1}|$ vertices.
 %\intertext{By \Cref{prop:queries-need-to-output-tuples} $\qruntime{Q_1,\dbbase} \geq |Q_1|$}
 %& \leq |V_{Q_1,\pxdb}| + 2 \qruntime{Q_1,\pxdb}\\
 \intertext{(From the inductive assumption)}
-& \leq (k-1)\qruntime{Q_1,\dbbase} + \abs{Q_1}\\
+& \leq k\qruntime{Q_1,\dbbase} + \abs{Q_1}\\
 \intertext{(By definition  of $\qruntime{Q,\dbbase}$)}
-& \le (k-1)\qruntime{Q,\dbbase}.
+& \le k\qruntime{Q,\dbbase}.
 \end{align*}
 \caseheading{Union}
 Assume that $Q = Q_1 \cup Q_2$.
@@ -243,23 +244,23 @@ The circuit for $Q$ has $|V_{Q_1,\pxdb}|+|V_{Q_2,\pxdb}|+|{Q_1} \cap {Q_2}|$ ver
 %\intertext{By \Cref{prop:queries-need-to-output-tuples} $\qruntime{Q_1,\dbbase} \geq |Q_1|$}
 %& \leq |V_{Q_1,\pxdb}|+|V_{Q_2,\pxdb}|+\qruntime{Q_1,\pxdb}+\qruntime{Q_2,\dbbase}|\\
 \intertext{(From the inductive assumption)}
-& \leq (k-1)(\qruntime{Q_1,\dbbase} + \qruntime{Q_2,\dbbase}) + (b_1 + b_2)
+& \leq k(\qruntime{Q_1,\dbbase} + \qruntime{Q_2,\dbbase}) + (|Q_1| + |Q_2|)
 \intertext{(By definition of $\qruntime{Q,\dbbase}$)}
-& \leq (k-1)(\qruntime{Q,\dbbase}).
+& \leq k(\qruntime{Q,\dbbase}).
 \end{align*}
 
-\caseheading{$k$-ary Join}
+\caseheading{$m$-ary Join}
-Assume that $Q = Q_1 \bowtie \ldots \bowtie Q_k$.
+Assume that $Q = Q_1 \bowtie \ldots \bowtie Q_m$. Note that $k=\sum_{i=1}^m k_i\ge m$.
-The circuit for $Q$ has $|V_{Q_1,\pxdb}|+\ldots+|V_{Q_k,\pxdb}|+(k-1)|{Q_1} \bowtie \ldots \bowtie {Q_k}|$ vertices.
+The circuit for $Q$ has $|V_{Q_1,\pxdb}|+\ldots+|V_{Q_k,\pxdb}|+(m-1)|{Q_1} \bowtie \ldots \bowtie {Q_k}|$ vertices.
 \begin{align*}
-|V_{Q,\pxdb}| & = |V_{Q_1,\pxdb}|+\ldots+|V_{Q_k,\pxdb}|+(k-1)|{Q_1} \bowtie \ldots \bowtie {Q_k}|\\
+|V_{Q,\pxdb}| & = |V_{Q_1,\pxdb}|+\ldots+|V_{Q_k,\pxdb}|+(m-1)|{Q_1} \bowtie \ldots \bowtie {Q_k}|\\
-\intertext{From the inductive assumption and noting $\forall i: k_i \leq k-1$}
+\intertext{From the inductive assumption and noting $\forall i: k_i \leq k$ and $m\le k$}
-& \leq (k-1)\qruntime{Q_1,\dbbase}+\ldots+(k-1)\qruntime{Q_k,\dbbase}+\\
+& \leq k\qruntime{Q_1,\dbbase}+\ldots+k\qruntime{Q_k,\dbbase}+\\
-&\;\;\; (k-1)|{Q_1} \bowtie \ldots \bowtie {Q_k}|\\
+&\;\;\; (m-1)|{Q_1} \bowtie \ldots \bowtie {Q_m}|\\
-& \leq (k-1)(\qruntime{Q_1,\dbbase}+\ldots+\qruntime{Q_k,\dbbase}+\\
+& \leq k(\qruntime{Q_1,\dbbase}+\ldots+\qruntime{Q_m,\dbbase}+\\
-&\;\;\;|{Q_1} \bowtie \ldots \bowtie {Q_k}|)\\
+&\;\;\;|{Q_1} \bowtie \ldots \bowtie {Q_m}|)\\
-\intertext{(By definition of $\qruntime{Q,\dbbase}$)}
+\intertext{(By definition of $\qruntime{Q,\dbbase}$ and assumption on $\jointime{\cdot}$)}
-& = (k-1)\qruntime{Q,\dbbase}.
+& \le k\qruntime{Q,\dbbase}.
 \end{align*}
 
 The property holds for all recursive queries, and the proof holds.
@@ -271,17 +272,17 @@ The property holds for all recursive queries, and the proof holds.
 
 We next need to show that we can construct the circuit in time linear in the deterministic runtime.  
 \begin{Lemma}\label{lem:tlc-is-the-same-as-det}
-Given a query $\query$ over a \dbbaseName $\dbbase$, the runtime $\timeOf{\abbrStepOne}(\query,\dbbase,\circuit) \le O(\qruntime{\query, \dbbase})$
+Given a query $\query$ over a \dbbaseName $\dbbase$ and the $\circuit^*$ output by \Cref{alg:lc}, the runtime $\timeOf{\abbrStepOne}(\query,\dbbase,\circuit^*) \le O(\qruntime{\query, \dbbase})$.
 \end{Lemma}
 \begin{proof}
-By analysis of \Cref{alg:lc}, invoked as $\abbrStepOne(\query, \dbbase, \emptyset, \emptyset, \emptyset)$.
+By analysis of \Cref{alg:lc}, invoked as $\circuit^*\gets\abbrStepOne(\query, \dbbase, \emptyset, \emptyset, \emptyset)$.
 
 We assume that $V$, $E$, and $\ell$ are each stored in a mutable accumulator with $O(1)$ ammortized append.
 We assume that $\phi$ is stored in a linked hashmap, with $O(1)$ insertions and retrievals, and $O(n)$ iteration over the domain of keys.
-We assume that the n-ary join $\domain(\phi_1) \bowtie \ldots \domain(\phi_n)$ can be computed in time $\jointime{\domain(\phi_1), \ldots, \domain(\phi_n)}$ and that an intersection $\domain(\phi_1) \cap \domain(\phi_2)$ can be computed in time $O(|\domain(\phi_1)| + |\domain(\phi_2)|)$ (i.e., with a hash table).
+We assume that the n-ary join $\domain(\phi_1) \bowtie \ldots \bowtie\domain(\phi_n)$ can be computed in time $\jointime{\domain(\phi_1), \ldots, \domain(\phi_n)}$ and that an intersection $\domain(\phi_1) \cap \domain(\phi_2)$ can be computed in time $O(|\domain(\phi_1)| + |\domain(\phi_2)|)$ (i.e., with a hash table).
 
 
-Before proving our runtime bound, we first observe that $\qruntime{\query, \db} \geq O(|\query(\db)|)$.
+Before proving our runtime bound, we first observe that $\qruntime{\query, \db} \geq \Omega(|\query(\db)|)$.
 This is true by construction for the relation, projection, and union cases, by \Cref{def:join-cost} for joins, and by the observation that $|\sigma(R)| \leq |R|$.
 
 We showthat $\qruntime{\query, \dbbase}$ is an upper-bound for the runtime of \Cref{alg:lc} by recursion.  
@@ -291,30 +292,30 @@ For the remaining cases, we make the recursive assumption that for every subquer
 \caseheading{Selection}
 Selection requires a recursive call to \Cref{alg:lc}, which by the recursive assumption is bounded by $O(\qruntime{\query', \dbbase})$.  
 \Cref{alg:lc} requires a loop over every element of $\query'(\dbbase)$.
-By the observation above that $\qruntime{\query, \db} \geq O(|\query(\db)|)$, this iteration is also bounded by $O(\qruntime{\query', \dbbase})$.
+By the observation above that $\qruntime{\query, \db} \geq \Omega(|\query(\db)|)$, this iteration is also bounded by $O(\qruntime{\query', \dbbase})$.
 
 \caseheading{Projection}
 Projection requires a recursive call to \Cref{alg:lc}, which by the recursive assumption is bounded by $O(\qruntime{\query', \dbbase})$, which in turn is a term in $\qruntime{\pi_{\vec{A}}\query', \dbbase}$.
 What remains is an iteration over $\pi_{\vec A}(\query(\dbbase))$ (lines 13--16), an iteration over $\query'(\dbbase)$ (lines 17--19), and the construction of a fan-in tree (line 20).
 The first iteration is $O(|\query(\dbbase)|) \leq O(\qruntime{\query, \dbbase})$.  
-The second iteration and the construction of the bounded fan-in tree are both $O(|\query'(\dbbase)|) \leq O(\qruntime{\query', \dbbase}) \leq O(\qruntime{\query, \dbbase}) $, by the the observation above that $\qruntime{\query, \db} \geq O(|\query(\db)|)$.
+The second iteration and the construction of the bounded fan-in tree are both $O(|\query'(\dbbase)|) \leq O(\qruntime{\query', \dbbase}) \leq O(\qruntime{\query, \dbbase}) $, by the the observation above that $\qruntime{\query, \db} \geq \Omega(|\query(\db)|)$.
 
 \caseheading{Bag Union}
-As above, the recursive calls explicitly correspond to terms in the expansion of $O(\qruntime{\query_1 \cup \query_2, \dbbase})$.  
+As above, the recursive calls explicitly correspond to terms in the expansion of $\qruntime{\query_1 \cup \query_2, \dbbase}$.  
 Initializing $\phi$ (line 24) can be accomplished in $O(\domain(\phi_1) + \domain(\phi_2)) = O(|\query_1(\dbbase)| + |\query_2(\dbbase)|) \leq O(\qruntime{\query_1, \dbbase} + \qruntime{\query_2, \dbbase})$.
 The remainder requires computing $\query_1 \cup \query_2$ (line 25) and iterating over it (lines 25--29), which is $O(|\query_1| + |\query_2|)$ as noted above --- this directly corresponds to terms in $\qruntime{\query_1 \cup \query_2, \dbbase}$.
 
 
-\caseheading{n-ary Join}
+\caseheading{$m$-ary Join}
 As in the prior cases, recursive calls explicitly correspond to terms in our target runtime.
-The remaining logic consists of computing $\domain(\phi_1) \bowtie \ldots \bowtie \domain(\phi_n)$, iterating over the results, and combining nodes in a fan-in tree.
+The remaining logic consists of computing $\domain(\phi_1) \bowtie \ldots \bowtie \domain(\phi_m)$, iterating over the results, and combining nodes in a fan-in tree.
-Respectively, these are $\jointime{\domain(\phi_1), \ldots, \domain(\phi_n)}$, $O(|\query_1(\dbbase) \bowtie \ldots \bowtie \query_n(\dbbase)|) \leq \jointime{\domain(\phi_1), \ldots, \domain(\phi_n)}$ (\Cref{def:join-cost}), and $O(k|\query_1(\dbbase) \bowtie \ldots \bowtie \query_n(\dbbase)|)$.
+Respectively, these are $\jointime{\domain(\phi_1), \ldots, \domain(\phi_m)}$, $O(|\query_1(\dbbase) \bowtie \ldots \bowtie \query_m(\dbbase)|) \leq O(\jointime{\domain(\phi_1), \ldots, \domain(\phi_m)})$ (\Cref{def:join-cost}), and $O(m|\query_1(\dbbase) \bowtie \ldots \bowtie \query_m(\dbbase)|)$.
 \qed
 \end{proof}
 
 
 
-With \Cref{lem:circ-model-runtime,lem:tlc-is-the-same-as-det} and our upper bound results on \approxq, we now have all the pieces to argue that using our approximation algorithm,  the expected multiplicities of an $\raPlus$ query can be computed in essentially the same runtime as deterministic query processing for the same query, proving claim (iv) of the Introduction.
+%With \Cref{lem:circ-model-runtime,lem:tlc-is-the-same-as-det} and our upper bound results on \approxq, we now have all the pieces to argue that using our approximation algorithm,  the expected multiplicities of an $\raPlus$ query can be computed in essentially the same runtime as deterministic query processing for the same query, proving claim (iv) of the Introduction.
 
 \section{Proof of \Cref{cor:cost-model}}
 \begin{proof}