Experimental note
Sequences of Posterior Cuts for Exact DNF Learning
A compact synthesis of the two posterior-collapse papers, plus a new transcript-level formalism for studying which membership and equivalence query sequences remove large parts of the surviving hypothesis space.
1. Common Posterior Formalism
Both papers start from the same finite exact-learning geometry. Let \(\mathcal X=\{0,1\}^n\), and let \(H_k\) be the set of Boolean functions representable by a DNF with at most \(k\) terms. A transcript \(\tau_t\) defines the version space
Under a full-support prior, the noiseless posterior is exactly supported on \(V_t\). Exact learning is therefore not merely posterior concentration. It is posterior collapse: every surviving hypothesis computes the same function on all of \(\mathcal X\).
Membership cuts
A membership query at \(x\) splits the posterior into labels \(0\) and \(1\). With \(p_t(x)=P_t[h(x)=1]\), the best local split has
Greedy membership can guarantee retained mass \(1-\alpha(V_t)\).
Equivalence cuts
A proposed hypothesis \(g\) lets the oracle choose a counterexample. The relevant worst-case retained posterior mass is
If \(\Lambda_t(g)\le 1-\beta\), every rejected equivalence query cuts at least a \(\beta\) fraction of the posterior.
2. What the Two Papers Add
The first paper gives a DNF-specific local mechanism. An equivalence query to \(g\equiv 0\) either proves the zero function or returns a positive witness \(x^+\). Since \(f(x^+)=1\), some DNF term fired at that point. Querying one-bit perturbations produces the local kill set
Each killed neighbor certifies that every term active at \(x^+\) contains the agreeing literal \(\lambda_i^{x^+}\). Under an isolation condition, these certified literals recover an entire term, which can be peeled from the residual DNF.
When this fails, the same paper turns the obstruction into structure. A nonredundant unpeelable term has private points whose one-bit boundary neighbors are rescued by other terms. This is the peel-or-overlap dichotomy.
The second paper gives the global mechanism. The posterior-majority function
is always central: \(\Lambda_t(g_t^{\mathrm{Maj}})\le 1/2\), and often much better. The bottleneck is representational. The majority vote over surviving \(k\)-term DNFs need not itself be a compact \(k\)-term DNF. Positive witnesses, peeling, and overlap compression are therefore preconditioners for the central problem: make a large-cut equivalence hypothesis compact enough to submit.
3. New Transcript-Level Formalism
Instead of analyzing a single query, define a query program as a sequence of the two allowed operations.
The sequence is adaptive: \(x_t\) and \(g_t\) may depend on the transcript so far. Each step induces a posterior-retention ratio
For a membership query at \(x\), the retained mass is the side consistent with \(f(x)\). For a rejected equivalence query to \(g\), the retained mass is the counterexample slice
Thus a sequence can be judged in two ways:
Raw cut power
Does the transcript shrink \(|V_t|\) quickly? Numerically, this is measured by \(c_t=1-|V_{t+1}|/|V_t|\) under the uniform finite prior.
Structural cut value
Does the transcript land inside a useful fiber, certify literals, peel a term, or expose an overlap boundary? Large cuts are most useful when they also simplify center construction.
4. Numerical Probe: Exact \(H_k\) on \(n=4\)
Distinct truth-table functions in \(H_k\) were enumerated for \(n=4\), with syntactic DNFs deduplicated by truth table. These spaces are small enough to compute exact version-space cuts. The first one-step comparison is especially revealing.
| \(k\) | \(|H_k|\) | Best MQ cut \(\alpha\) | Majority-EQ guaranteed cut \(1-\alpha\) | Best legal \(H_k\)-EQ retained |
|---|---|---|---|---|
| 1 | 82 | 0.195 | 0.805 | 0.195 |
| 2 | 1,886 | 0.320 | 0.680 | 0.320 |
| 3 | 15,358 | 0.418 | 0.582 | 0.418 |
| 4 | 44,262 | 0.472 | 0.528 | 0.472 |
| 5 | 61,294 | 0.495 | 0.505 | 0.495 |
The best membership query cuts only the smaller side. A posterior-majority equivalence query forces the oracle into that smaller side, so the cut is complementary. Early sparse DNF spaces are very skewed, making \(EQ(0)\) and majority-like proposals powerful.
5. Sequence Experiments
Adaptive sequences were then simulated with adversarial equivalence counterexamples. For \(n=4,k=3\), over 80 sampled targets:
| Policy | Mean queries | Median queries | Max queries | Mean cut/query |
|---|---|---|---|---|
| Greedy membership | 15.44 | 15.0 | 17 | 0.477 |
| EQ to posterior majority | 9.56 | 10.0 | 12 | 0.583 |
| EQ to best legal \(H_k\) center | 10.49 | 11.0 | 13 | 0.557 |
| Crude one-step hybrid | 11.10 | 11.0 | 15 | 0.555 |
The hybrid simply chose the better immediate worst-case cut between a membership split and a legal-DNF center. It was not a structural policy, so it did not exploit witness fibers or overlap certificates.
The second-paper claim also appears in a small representability check. In 936 posterior states visited by majority-EQ traces for \(n=4,k=3\), the exact posterior-majority truth table was itself in \(H_k\) about 75.2% of the time. When it was not, the best legal \(H_k\)-center was usually close: the average retained-mass gap was about 0.008, though the worst observed gap was 0.167.
6. Positive-Witness Star Cuts
The most informative structural sequence was not a pure center sequence. It was the positive-witness star:
For \(n=4,k=3\), over 80 sampled nonzero targets, this short transcript left only a tiny fraction of the finite \(H_k\) posterior.
| Witness choice | Mean retained mass | Mean cut | Mean killed neighbors |
|---|---|---|---|
| Random positive witness | 0.0258 | 0.974 | 2.42 |
| Best positive witness | 0.0234 | 0.977 | 2.79 |
The point is not just that the posterior shrinks. The transcript lands in a DNF-specific fiber. The killed neighbors are certified active literals; if the witness is isolated, the transcript recovers a term. If not, the failed isolation records which one-bit boundaries are rescued by other terms.
7. Random Syntactic DNF Probe
To connect the finite truth-table cuts to the first paper's geometry, random fixed-width DNFs were sampled and each term was classified as peelable, redundant, or nonredundant-unpeelable. The probe also measured how often private boundary edges were rescued by other terms.
| \(n,k,r\) | Peelable | Redundant | Unpeelable | Private density | Rescue rate | Best witness peels? | Min new vars in rescuer |
|---|---|---|---|---|---|---|---|
| 10,16,4 | 0.830 | 0.002 | 0.168 | 0.384 | 0.322 | 1.000 | 1.16 |
| 10,32,4 | 0.174 | 0.064 | 0.762 | 0.144 | 0.541 | 0.992 | 1.20 |
| 12,32,4 | 0.539 | 0.009 | 0.452 | 0.136 | 0.479 | 1.000 | 1.31 |
| 12,48,4 | 0.094 | 0.067 | 0.839 | 0.051 | 0.640 | 0.875 | 1.32 |
Stacked bars show peelable/redundant/unpeelable term fractions. The number at right is the rescue rate. As formulas get denser, peeling falls and rescued boundary overlap rises.
8. Interpretation
The experimental picture ties the papers together as follows:
The central claim of the second paper is strengthened by the sequence view: the oracle can supply large posterior cuts, but the learner has to submit a representable center. The positive-witness and peel-or-overlap machinery from the first paper is one plausible way to make those centers representable by simplifying the residual geometry.
9. Next Formal Target
The numerical probes suggest a sharper theorem template. A preconditioning transcript should be evaluated by the pair
where the first coordinate is posterior mass retained and the second is a certificate that the residual geometry admits compact centers. A useful theorem would say that if peeling stalls, the rescued-boundary graph compresses the residual enough to construct a \(\beta\)-central hypothesis with \(\beta=\Omega(1)\) or with a reduced effective parameter.
This is still a conjectural route, but the experiments make the direction concrete: search over adaptive sequences not only for large cuts, but for cuts that produce witnesses, fibers, peel certificates, and compressed overlap graphs.
Reproducibility Note
The exact \(n=4\) experiments and sequence simulations were generated
from cut_sequence_experiments.py. The random syntactic probe
sampled fixed-width terms and classified terms by private points,
isolation, and rescued one-bit boundaries. The numbers are intended as
geometry probes, not asymptotic evidence.