Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 57 tok/s
Gemini 2.5 Pro 52 tok/s Pro
GPT-5 Medium 20 tok/s Pro
GPT-5 High 19 tok/s Pro
GPT-4o 93 tok/s Pro
Kimi K2 176 tok/s Pro
GPT OSS 120B 449 tok/s Pro
Claude Sonnet 4.5 35 tok/s Pro
2000 character limit reached

Spectral Initialization for High-Dimensional Phase Retrieval with Biased Spatial Directions (2403.15548v1)

Published 22 Mar 2024 in cond-mat.dis-nn, cs.IR, and math.PR

Abstract: We explore a spectral initialization method that plays a central role in contemporary research on signal estimation in nonconvex scenarios. In a noiseless phase retrieval framework, we precisely analyze the method's performance in the high-dimensional limit when sensing vectors follow a multivariate Gaussian distribution for two rotationally invariant models of the covariance matrix C. In the first model C is a projector on a lower dimensional space while in the second it is a Wishart matrix. Our analytical results extend the well-established case when C is the identity matrix. Our examination shows that the introduction of biased spatial directions leads to a substantial improvement in the spectral method's effectiveness, particularly when the number of measurements is less than the signal's dimension. This extension also consistently reveals a phase transition phenomenon dependent on the ratio between sample size and signal dimension. Surprisingly, both of these models share the same threshold value.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (18)
  1. E. J. Candes, T. Strohmer, and V. Voroninski, “Phaselift: Exact and stable signal recovery from magnitude measurements via convex programming,” Communications on Pure and Applied Mathematics, vol. 66, no. 8, pp. 1241–1274, 2013.
  2. R. Balan, P. Casazza, and D. Edidin, “On signal reconstruction without phase,” Applied and Computational Harmonic Analysis, vol. 20, no. 3, pp. 345–356, 2006.
  3. M. Fickus, D. G. Mixon, A. A. Nelson, and Y. Wang, “Phase retrieval from very few measurements,” Linear Algebra and its Applications, vol. 449, pp. 475–499, 2014.
  4. T. Heinosaari, L. Mazzarella, and M. M. Wolf, “Quantum tomography under prior information,” Communications in Mathematical Physics, vol. 318, no. 2, pp. 355–374, 2013.
  5. A. S. Bandeira, J. Cahill, D. G. Mixon, and A. A. Nelson, “Saving phase: Injectivity and stability for phase retrieval,” Applied and Computational Harmonic Analysis, vol. 37, no. 1, pp. 106–125, 2014.
  6. A. Conca, D. Edidin, M. Hering, and C. Vinzant, “An algebraic characterization of injectivity in phase retrieval,” Applied and Computational Harmonic Analysis, vol. 38, no. 2, pp. 346–356, 2015.
  7. C. Vinzant, “A small frame and a certificate of its injectivity,” in 2015 International Conference on Sampling Theory and Applications (SampTA).   IEEE, 2015, pp. 197–200.
  8. R. W. Gerchberg, “A practical algorithm for the determination of plane from image and diffraction pictures,” Optik, vol. 35, no. 2, pp. 237–246, 1972.
  9. I. Waldspurger, “Phase retrieval with random gaussian sensing vectors by alternating projections,” IEEE Transactions on Information Theory, vol. 64, no. 5, pp. 3301–3312, 2018.
  10. E. J. Candes, X. Li, and M. Soltanolkotabi, “Phase retrieval from coded diffraction patterns,” Applied and Computational Harmonic Analysis, vol. 39, no. 2, pp. 277–299, 2015.
  11. P. Schniter and S. Rangan, “Compressive phase retrieval via generalized approximate message passing,” IEEE Transactions on Signal Processing, vol. 63, no. 4, pp. 1043–1055, 2014.
  12. W. Luo, W. Alghamdi, and Y. M. Lu, “Optimal spectral initialization for signal recovery with applications to phase retrieval,” IEEE Transactions on Signal Processing, vol. 67, no. 9, pp. 2347–2356, 2019.
  13. Y. M. Lu and G. Li, “Phase transitions of spectral initialization for high-dimensional non-convex estimation,” Information and Inference: A Journal of the IMA, vol. 9, no. 3, pp. 507–541, 2020.
  14. M. Mondelli and A. Montanari, “Fundamental limits of weak recovery with applications to phase retrieval,” in Conference On Learning Theory.   PMLR, 2018, pp. 1445–1450.
  15. M. Potters and J.-P. Bouchaud, “A first course in random matrix theory: Erratum,” 2022, https://www.cambridge.org/files/8616/5539/3252/Erratum_FCRMT.pdf.
  16. R. Speicher, “Free probability theory, chapter 22 in the oxford handbook of random matrix theory, 1st edn., editors: G. akemann, j. baik and p. di francesco,” 2011.
  17. Z. Burda, “Free products of large random matrices–a short review of recent developments,” in Journal of Physics: Conference Series, vol. 473, no. 1.   IOP Publishing, 2013, p. 012002.
  18. J. Bun, R. Allez, J.-P. Bouchaud, and M. Potters, “Rotational invariant estimator for general noisy matrices,” IEEE Transactions on Information Theory, vol. 62, no. 12, pp. 7475–7490, 2016.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up