- Rating
- 2(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper, “Learning Interpretable Oblivious Trees with Variational Quantum Circuits,” introduces Quantum Oblivious Decision Trees (QODTs), a variational quantum learning framework designed to combine the interpretability of classical decision trees with quantum circuit-based optimization. The main contributions are three circuit architectures: (1) General, which employs conventional variational quantum circuits with angle encoding; (2) Structured, which explicitly represents each tree level using a phase-based quantum comparator with a trainable threshold; and (3) Recycle, which reuses a single comparator qubit through mid-circuit measurement, reset, and classical feed-forward. The latter two architectures allow learned feature-threshold relationships to be extracted and used to reconstruct classical oblivious decision trees. The recycle architecture is particularly noteworthy for maintaining a constant qubit count as tree depth increases.
Critical strengths
-
A notable theoretical strength is the incorporation of oblivious decision-tree structure into the variational quantum circuit through phase-based quantum comparators. In the structured and recycle architectures, each decision level corresponds to an explicit feature-threshold comparison, allowing the learned splitting conditions to be recovered from circuit parameters. This establishes a meaningful connection between the mathematical structure of classical decision trees and parameterized quantum circuits. The approach is particularly valuable because it introduces an interpretable inductive bias into quantum model design, rather than relying entirely on generic variational ansätze.
-
The recycle architecture provides a theoretically motivated approach to reducing quantum resource requirements while preserving the intended decision-tree structure. By combining mid-circuit measurement, qubit reset, and classical feed-forward, the number of required qubits becomes independent of tree depth, decreasing from (d+w) in the structured architecture to (1+w). This construction offers a clear architectural trade-off between qubit resources and sequential circuit execution. Its significance lies in demonstrating how classical control and quantum operations can be combined to represent increasingly deep decision structures without a corresponding increase in qubit count.
Critical weaknesses
-
Although the structured and recycle architectures explicitly incorporate feature-threshold comparisons, the paper does not establish sufficient theoretical conditions under which the reconstructed classical decision tree faithfully reproduces the quantum model. In particular, the authors acknowledge that the thresholds in the structured architecture are not uniquely identifiable because subsequent variational operations can compensate for changes in their values. Moreover, the reconstruction procedure assigns leaf labels using the majority class of the training samples rather than directly recovering the quantum circuit's prediction mechanism. Consequently, extracting the learned thresholds does not necessarily yield a functionally equivalent classical tree. This limitation is consequential because interpretability is a central motivation of the proposed framework, yet the relationship between parameter interpretability and predictive equivalence remains insufficiently established.
-
The recycle architecture is presented as a more resource-efficient and trainable alternative, primarily based on its constant qubit count and slower empirical gradient-variance decay. However, the paper does not provide a theoretical characterization of gradient scaling or establish conditions under which the architecture avoids severe optimization difficulties as tree depth increases. Furthermore, reducing the number of qubits introduces additional sequential measurements, resets, classical feed-forward operations, and variational parameters, whose combined computational costs are not theoretically quantified. Without a more complete complexity analysis, it remains unclear whether the observed improvements in qubit efficiency and gradient behavior translate into a meaningful computational advantage. This weakens the broader significance of the proposed architecture beyond the numerical settings considered.
Questions for authors
Q1: In Section 4.2, the authors reconstruct classical oblivious decision trees by extracting the learned feature-threshold pairs and assigning leaf labels according to the majority class of the corresponding training samples. However, Section 5.2 reports an average accuracy reduction of 2.9 percentage points for the structured architecture, with a particularly substantial decrease on the banknote dataset (from 92.8% to 68.8%). Could the authors clarify under what mathematical conditions the reconstructed classical tree can be considered functionally equivalent to the original quantum classifier? In particular, how does the non-identifiability of threshold parameters in the structured architecture affect the theoretical validity of the claimed interpretability?
Q2: Figure 3 demonstrates that the recycle architecture exhibits a slower empirical decay in gradient variance as tree depth increases. However, the analysis appears to rely primarily on numerical observations and fitted decay exponents. Could the authors provide a more rigorous explanation of how mid-circuit measurement, qubit reset, and classical feed-forward influence gradient propagation across successive decision levels? Specifically, is there a theoretical argument supporting the observed improvement in gradient scaling, or could this behavior depend on the selected ansatz, initialization strategy, and dataset characteristics?
Q3: The recycle architecture reduces the qubit requirement from (d+w) to (1+w), but introduces sequential comparator operations and classically conditioned variational blocks at each decision level. Could the authors clarify how the total computational cost scales with tree depth when circuit executions, measurement shots, reset latency, feed-forward operations, and trainable parameters are considered together? This distinction would help establish whether the reduction in qubit count provides a practical resource advantage rather than a trade-off that shifts computational overhead to circuit execution.
3 comments
I've revised the scores in recognition of your efforts.
Thank you for revisiting the paper and for raising your score. We appreciate your feedback, which pushed us to add the theoretical results (prop 1 and 2) that now ground the paper.
Thank you for pushing on theory; we agree it was missing, and the revision adds it (changes highlighted in blue in the revised PDF).
Conditions for faithful reconstruction (W1, Q1). Proposition 1 (Sec. 4, proof in App. F) gives the exact form of recycle: ⟨Z⟩(x)=∑bπb(x)g(b), a soft oblivious tree whose leaf values g(b) are read from the circuit. Corollary 1 gives the conditions under which the hard tree T(x)=g(b∗) reproduces the circuit: ∣⟨Z⟩−T∣≤2(1−π∗), and the two predict the same class whenever π∗(x)>1/(1+∣T(x)∣), where π∗ is the probability of the hard path. Functional equivalence therefore holds exactly in the sharp-comparator limit π∗→1. Empirically, the hard tree agrees with the circuit on 90.7% of test predictions (Table 2). For structured no such decomposition exists: its thresholds can be absorbed by the ansatz (App. D), and only 63.3% of predictions agree, so we now restrict the claim of faithful extraction to recycle. This also explains the banknote case (92.8% → 68.8%).
Gradient scaling (W2, Q2). Proposition 2 (App. F, with proof) shows that for Haar-random blocks Var[∂ϕ⟨Z⟩]=Vw(pi(c))2∏j=iqj, where qj=pj2+(1−pj)2=21(1+sin2(xj−tj))∈[21,1]. Mid-circuit measurement turns the circuit into a classical mixture over decision paths, so the cross-path terms of the gradient vanish. The register width, and hence Vw, does not grow with depth, and each additional level multiplies the variance by a factor between 21 (maximally uncertain split) and 1 (deterministic split), whereas a Haar-random circuit on d+w qubits loses a factor 2 per level regardless. The measured decay rates (App. E, Figure 10) are 0.42–0.69 per level for recycle at w=2, against 0.82–1.51 for general and structured. So yes, the rate depends on the data, through qj, and on the ansatz, through how close the blocks are to Haar-random; the ansatz ablation of App. I shows that the advantage of recycle is preserved under two other ansätze.
Total cost (W2, Q3). App. D quantifies qubits, gates, sequential depth, mid-circuit measurements, resets, feed-forward steps, parameters, evaluations per gradient and wall-clock time (Table 9). We agree that the qubit reduction is a trade-off, not a free saving, and the paper now says so.
Ethics flag. The revised PDF now includes an ethics statement: all datasets are public tabular benchmarks commonly used in machine learning, and no human subjects or new data are involved. We are happy to address any specific concern.