- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3(+1)
- Soundness
- 2(+1)
Read review
Paper summary
So, this paper is all about why PQCs with the same number of parameters generalize differently. The authors frame this question around QRL policies and relevant value functions. Now on the theory side, Thm 1 is sort of the pretty standard McAllester-Maurer PAC-Bayes generalization bounds for iid environments. The authors proceed to Thm 2 which takes an isotropic Gaussian prior and a Gauss-Newton posterior such that the KL term picks up a Fisher log-determinant, ok. Then Prop 1 goes on and shows that the backward causal cone of a local readout can only grow when entangling gates are added, which caps the Fisher rank. Finally the authors say that only this cone monotonicity is proved and the step from rank to to the gap is treated as empirical.
Regarding the experiments conducted the authors use a small test bed with a 300 point correlation grid, together with a matched CNOT control and a global readout control, scaling to n=16 (which is for 2026 standards a bit low) then Monte-Carlo value regression, REINFORCE over four small real datasets and one (again, needs be more) IBM Heron run. The main finding is that at fixed the gap grows with connectivity and with , and predicts the gap better than benchmark.
Critical strengths
First, the authors are honest about their work and its strenghts/weaknesses. They do separate proved from measured claims (for example Figure 1 and Remark 2) and report results that cut against its own story. And honenstly this kind of reporting is rare in quantum ML and makes the empirical picture easier to trust while it also demonstrates the hardness of the field.
Now, the derivation the paper mosty relies on is correct and checkable (and I checked with AI and was able to re-derived Eq. (2) and found that the dropped term is non-negative, so dropping it is conservative (authors better recheck). Also Remark 1 is right that gamma can depend on the data without a union bound since it only shapes the posterior. Also Table 2 bound values can be reproduced from the stated C, m and delta, and several controls are really quite informative.
Critical weaknesses
The unentangled baseline differs in feature access and not just entanglement. With product encoding, no two-qubit gates and a Pauli readout, the circuit factorizes and the output depends only on x_1 and the appendix itself gives ⟨Z_0⟩ so none is a rank-2 model of one feature, while linear and full see all four. Then, a smaller gap is what any capacity measure would predict really? On the PCA datasets, none is a classifier on the first principal component and the matched-CNOT disjoint control is identical to none by construction. The global readout control makes the point directly actually since a no-entanglement (classical) circuit reaches d_eff 14.0 and gap 0.095, about the same as the local full circuit (12.9, 0.104) and (again, nicely) the authors accept this objection as the mechanism, but then what is left is that higher effective capacity gives a larger gap and realy this is well known which weakens the main claim. The title and abstract still present entanglement as an independent complexity aspect (hard one) for which I don't think the evidence supports that, maybe not at the level for acceptance.
As far as the theory is concerned, it is arguably quite thin. d_eff enters the bound mainly through the choice of posterior, Thm 2 is a Gaussian KL identity and Prop 1 is graph reachability. In general, circuits with more curved directions are penalized more because the posterior was sharpened more and a fair comparison would optimize the posterior per circuit. Separately AI catched this: the certificate is vacuous relative to chance in every cell ie implied test-error bounds are about 0.60 for none at N=64, above 0.9 for full at N=16, and about 0.54 in the best case. (non-vacuous should go.)
A few smaller issues: Lemma 1 is applied to 0/1 accuracy gaps and does not cover, and τ^2=1 is hardly local. Also, the bandit has two actions, so a zero reward reveals the label, and it is classification with a different loss and the value-function task is regression.
Questions for authors
- Can you build an unentangled baseline that sees all inputs at matched d, for example re-uploading all features onto wire 0, or comparing entangled and product circuits under a global readout at matched live-parameter count? Does any entanglement measure still predict the gap at fixed d_eff? This is the question that matters most for my score.
- What are rho(d_eff, gap), rho(norm, gap) and their difference within each N (and each N, L), with the bootstrap clustered by design cell?
- For each circuit, what is the best certificate over a posterior family that includes N(theta, tau^2)? Does the none < entangled ordering survive?
- Disclose how many hardware seeds were run, and can you report test accuracies with error bars?
- Can the bandit result be shown with K>2 actions, where zero reward does not reveal the label?
2 comments
We thank the reviewer for the follow-up and for raising Soundness. We have made the three changes you listed. The updated PDF is uploaded (table numbers refer to it; new changes are in blue).
1. Title and framing around Fisher log-determinant complexity
- Title is now "Beyond Parameter Count: A PAC-Bayesian View of Fisher Complexity and Generalization in Quantum Policies and Value Functions".
- Contribution 2 is now "Fisher complexity, not parameter count, tracks the gap". It states that the gap follows at fixed for product and entangled circuits alike. Entangling connectivity is presented as one structural route to a larger , alongside global readout and data re-uploading. Once is controlled, the entangling power carries no further information.
- Introduction. "None isolates entanglement as the governing complexity" is replaced. The pathway paragraph now starts from circuit structure rather than from entanglement.
- Also reworded: the abstract, Related Work, the Section 4 title ("Entangling Connectivity Raises Fisher Complexity at Fixed Parameter Count"), the Figure 1 caption, the Discussion, and captions that called the gap "the entanglement cost".
- "Entangled circuits generalize worse". Every remaining sentence of this form (Section 6; Appendix B near Tables 6, 14 and 21) is now scoped to the controlled setting with fixed encoding and readout.
- Why entanglement remains in the experiments. It is the variable we manipulate in the controlled sweeps, because it changes while , the encoding and the readout stay fixed. No claim rests on entanglement beyond that.
2. Feature-complete baselines in the policy setting (new Table 16, paragraph in Section 6)
Protocol. Both bandits use their original protocols unchanged; only the circuit family varies.
- Common to both: , 16 seeds, , 816 runs.
- : the circuit families of Table 3.
- (Born policy on wires 0,1):
- a re-uploading circuit whose two readout wires jointly see all four features, with none/linear/full connectivity;
- a two-wire product circuit in which each readout wire cycles through all four features.
The none/linear/full rows are reruns of Tables 14 and 15 and lie within about one s.e. of them.
Results. The picture matches supervised classification.
| within | (entangling power, gap) | partial of entangling power given | |
|---|---|---|---|
| 0.73 – 0.81 | 0.10 – 0.13 | −0.13 – −0.04 | |
| 0.61 – 0.79 | 0.12 – 0.22 | −0.10 – 0.00 |
Gap at (± s.e.):
local none | local full | product, sees all features (largest ) | |
|---|---|---|---|
| 0.069 ± 0.018 | 0.156 ± 0.015 | 0.369 ± 0.012 (1-qubit re-upload, 46.1) | |
| 0.139 ± 0.018 | 0.258 ± 0.017 | 0.417 ± 0.013 (2-wire re-upload, 54.4) |
The policies with no entangling gates and the most feature access have the largest and the largest gaps. They also have the lowest test reward (0.26 for the 2-wire policy at , chance 0.25), so the table supports as a predictor of the gap, not of test reward; the paper now says this explicitly and does not equate a larger gap with worse test performance.
Within a fixed encoding and readout, connectivity still raises the gap in 29 of 30 paired comparisons:
- : 17 of 18. The local readout gives 3.5 to 9.7 s.e., re-uploading 2.7 to 5.4 s.e., and the global readout −0.4 to 2.6 s.e.
- : 12 of 12, at 2.4 to 8.3 s.e.
As in classification, the gap tracks , not entanglement.
3. Certificate claim narrowed (Table 2, Section 5, abstract, Discussion)
You are right that the certificate responds to complexity rather than to entanglement. Table 2 now includes the two unentangled circuits that see every feature, next to their :
| circuit | bound | |||
|---|---|---|---|---|
none (local) | 2.6 | 0.729 | 0.589 | 0.504 |
linear (local) | 7.9 | 0.727 | 0.603 | 0.524 |
full (local) | 12.8 | 0.801 | 0.618 | 0.519 |
none, global readout | 14.1 | 0.809 | 0.674 | 0.561 |
| re-upload, 1 qubit | 43.5 | 0.819 | 0.656 | 0.565 |
The text now claims only what Tables 2 and 5 to 7 support:
- it separates circuits of equal whose Fisher complexity differs widely: the single-feature
nonelies belowfullat every ; - it does not order every pair:
noneandlinearare tied at (0.729 vs 0.727),linearandfullat (0.524 vs 0.519), andlinearis separated fromnoneonly at ; - it does not separate entangled circuits from feature-complete product circuits, which receive bounds as loose as
fullor looser.
The abstract and Limitations say the same ("it does not order every pair of circuits and does not single out entanglement").
The authors ran every experiment I asked for and corrected two errors in the original submission themselves. The main claims now largely match the evidence, so I am raising Soundness from 1 to 2. My rating stays at weak rejection for now, for three reasons.
First, the key experiment went against the original framing. Once D_eff is controlled for, entanglement does not predict the gap as it seems. Yet the paper title, contribution #3, the introduction and parts of the appendix still present entanglement as the governing complexity which is odd to me.
Second, the certificate only clearly separates "full" from the "none" circuit that sees just one feature. Unentangled circuits that see all features get bounds as loose as full. So the certificate is again picking up feature access and not entanglement.
Finally, the policy and value-function experiments still compare against the one-feature "none" baseline. The feature-complete baselines exist only for supervised classification.
I would move to weak acceptance with three changes: a title and text framed around Fisher log-det complexity, a feature-complete baseline in at least one policy setting (eg., the 4-action bandit), and a certificate claim narrowed to what Tables 4, 6 and 7 support.