- Rating
- 4(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes robust quantile Writinger flow (RQWF) for complex phase retrieval without noise moments. RQWF consistts a clipped spectral initialization with quantile-based radial calibration and a bounded-score Writinger flow refinement. Under complex random Gaussian measurement vectors and local regularity assumptions on noise, an end-to-end finite-sample recovery guarantee is proved, with rates matching a Cauchy lower bound up to log factors. Experimental results show benefits that vary across different noise regimes.
Critical strengths
-
The end-to-end finite-sample recovery guarantee without noise-moment assumptions. The theory is proved under complex random Gaussian measurements and it is assumed only the local noise-density regularity. The recovery rate matches a Cauchy lower bound up to log factors. It establishes statistically accurate, computationally attainable recovery in regime excluded by finite-moment theory. It is a substantive theoretial contribution.
-
The technical contributions in the proofs, including a moment-free spectral gap (Lemma 13), 2nd-order radial calibration error (Lemma 14), uniform gradient control and sample reuse (Lemma 11), and sharp bias analysis (Proposition 5). These results also provide technical depth of this paper.
Critical weaknesses
-
Insufficient application and justification for the quantile-noise model. The noise model is primarily a theoretical statistical model for recovery without noise-moment assumptions. The practical relevance of the prescribed non-median quantile remains insufficiently demonstrated. The optical experiment (Section 6) adds simulated noise to the recorded measurements.
-
Gaps between the analyzed algorithm and the one with the strongest emprical advantage. For examples, (a) the analyzed RQWF-T uses separate samples for spectral estimation, radial calibration, and refinement, but the emprical RQWF-P reuses all data; (b) the clipping threshold is fixed beforehand in RQWF-T but estimated from data in RQWF-P.
Questions for authors
-
Can the authors describe a concrete measurement setting where the true intensity satisfies , particularly for ? How would you prescribed be determined or calibrated before reconstruction?
-
How essential are sample splitting and fixed clipping to the recovery analysis? Can the authors clarify how the guarantees relate to RQWF-P's stronger empirical performance, given its full data reuse and data-dependent clippling?