Pith. sign in

REVIEW 117 references

Optimal spectral initializers impact on phase retrieval phase transitions -- an RDT view

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.18279 v1 pith:I444DO2A submitted 2025-06-23 stat.ML cs.ITcs.LGmath.IT

Mihailo Stojnic This is my paper · ORCID
classification stat.MLcs.ITcs.LGmath.IT
keywords emphphasealphamathcaloptspinsregionstheoreticaldprs
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We analyze the relation between spectral initializers and theoretical limits of \emph{descending} phase retrieval algorithms (dPR). In companion paper [104], for any sample complexity ratio, $\alpha$, \emph{parametric manifold}, ${\mathcal {PM}}(\alpha)$, is recognized as a critically important structure that generically determines dPRs abilities to solve phase retrieval (PR). Moreover, overlap between the algorithmic solution and the true signal is positioned as a key ${\mathcal {PM}}$'s component. We here consider the so-called \emph{overlap optimal} spectral initializers (OptSpins) as dPR's starting points and develop a generic \emph{Random duality theory} (RDT) based program to statistically characterize them. In particular, we determine the functional structure of OptSpins and evaluate the starting overlaps that they provide for the dPRs. Since ${\mathcal {PM}}$'s so-called \emph{flat regions} are highly susceptible to \emph{local jitteriness} and as such are key obstacles on dPR's path towards PR's global optimum, a precise characterization of the starting overlap allows to determine if such regions can be successfully circumvented. Through the presented theoretical analysis we observe two key points in that regard: \textbf{\emph{(i)}} dPR's theoretical phase transition (critical $\alpha$ above which they solve PR) might be difficult to practically achieve as the ${\mathcal {PM}}$'s flat regions are large causing the associated OptSpins to fall exactly within them; and \textbf{\emph{(ii)}} Opting for so-called ``\emph{safer compression}'' and slightly increasing $\alpha$ (by say $15\%$) shrinks flat regions and allows OptSpins to fall outside them and dPRs to ultimately solve PR. Numerical simulations are conducted as well and shown to be in an excellent agreement with theoretical predictions.

Discussion (0). Continue with ORCID to comment.

Reference graph

Works this paper leans on

117 extracted references · 14 linked inside Pith

  1. [1]

    Achlioptas, A

    D. Achlioptas, A. Coja-Oghlan, and F. Ricci-Tersenghi. On the solution-space geometry of random constraint satisfaction problems. Random Struct. Algorithms , 38(3):251–268, 2011

    2011

  2. [2]

    Ahmed, B

    A. Ahmed, B. Recht, and J. Romberg. Blind deconvolution u sing convex programming. IEEE Trans- actions on Information Theory , 60(3):1711–1732, 2013

    2013

  3. [3]

    Aubin, B

    B. Aubin, B. Loureiro, A. Baker, F. Krzakala, and L. Zdebo rová. Exact asymptotics for phase retrieval and compressed sensing with random generative priors. In Proceedings of Mathematical and Scientific Machine Learning, MSML 2020, 20-24 July 2020, Virtual Confere nce / Princeton, NJ, USA , volume 107 of Proceedings of Machine Learning Research , pages 55–...

    arXiv 2020

  4. [4]

    Bahmani and J

    S. Bahmani and J. Romberg. Phase retrieval meets statist ical learning theory: A flexible convex relaxation. Electronic Journal of Statistics , 11:5254–5281, 2016. 23

    2016

  5. [5]

    Balan, B

    R. Balan, B. Bodmann, P. Casazza, and D. Edidin. Painless reconstruction from magnitudes of frame coefficients. J. Four. Anal. Appl. , 15:488–501, 2009

    2009

  6. [6]

    Balan, P

    R. Balan, P. Casazza, and D. Edidin. On signal reconstruc tion without phase. Applied and Computa- tional Harmonic Analysis , 20(3):343–356, 2006

    2006

  7. [7]

    Baldassi, A

    C. Baldassi, A. Ingrosso, C. Lucibello, L. Saglietti, an d R. Zecchina. Subdominant dense clusters allow for simple learning and high computational performance in n eural networks with discrete synapses. Physical Review letters , 115(12):128101, 2015

    2015

  8. [8]

    Baldassi, A

    C. Baldassi, A. Ingrosso, C. Lucibello, L. Saglietti, an d R. Zecchina. Local entropy as a measure for sampling solutions in constraint satisfaction problems. Journal of Statistical Mechanics: Theory and Experiment, (2):021301, 2016

    2016

Show all 117 references
  1. [9]

    Baldassi, R

    C. Baldassi, R. D. Vecchia, C. Lucibello, and R. Zecchina . Clustering of solutions in the symmetric binary perceptron. Journal of Statistical Mechanics: Theory and Experiment , (7):073303, 2020

    2020

  2. [10]

    A. S. Bandeira, J. Cahill, D. G. Mixon, and A. A. Nelson. S aving phase: Injectivity and stability for phase retrieval. Applied and Computational Harmonic Analysis , 37(1):106–125, 2014

    2014

  3. [11]

    Barbier, F

    J. Barbier, F. Krzakala, N. Macris, L. Miolane, and L. Zd eborová. Optimal errors and phase transi- tions in high-dimensional generalized linear models. In Conference On Learning Theory, COLT 2018, Stockholm, Sweden, 6-9 July 2018 , volume 75 of Proceedings of Machine Learning...

    2018 arXiv

  4. [12]

    A. Bora, A. Jalal, E. Price, and A. G. Dimakis. Compresse d sensing using generative models. In Proceedings of the 34th International Conference on Machine L earning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 , volume 70 of Proceedings of Machine Learning Research , ...

    2017

  5. [13]

    Bruck and L.G

    Y.M. Bruck and L.G. Sodin. On the ambiguity of the image r econstruction problem. Opt. Comm. , 30:304–308, 1979

    1979

  6. [14]

    O. Bunk, A. Diaz, F. Pfefer, C. David, B. Schmitt, D. K. Sa tapathy, and J. F. Veen. Diffractive imaging for periodic samples: retrieving one-dimensional concent ration profies across microuidic channels. Acta Crystallographica Section A: Foundations of Crystallograph y, 63(4):3...

    2007

  7. [15]

    K. Wang C. Ma, Y. Chi, and Y. Chen. Implicit regularizati on in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, m atrix completion, and blind deconvolution. Foundations of Computational Mathematics , pages 1–182, 2018

    2018

  8. [16]

    T T. Cai, X. Li, and Z. Ma. Optimal rates of convergence fo r noisy sparse phase retrieval via thresholded Wirtinger flow. The Annals of Statistics , 44(5):2221–2251, 2016

    2016

  9. [17]

    E. J. Candès, Y. C. Eldar, T. Strohmer, and V. Voroninski . Phase retrieval via matrix completion. SIAM J. Imaging Sci. , 6(1):199–225, 2013

    2013

  10. [18]

    E. J. Candès and X. Li. Solving quadratic equations via p haselift when there are about as many equations as unknowns. Found. Comput. Math. , 14(5):1017–1026, 2014

    2014

  11. [19]

    E. J. Candès, X. Li, and M. Soltanolkotabi. Phase retrie val from coded diffraction patterns. Applied and Computational Harmonic Analysis , 39(2):277–299, 2015

    2015

  12. [20]

    E. J. Candès, X. Li, and M. Soltanolkotabi. Phase retrie val via Wirtinger flow: Theory and algorithms. IEEE Trans. Inf. Theory , 61(4):1985–2007, 2015

    1985

  13. [21]

    E. J. Candès, T. Strohmer, and V. Voroninski. Phaselift : Exact and stable signal recovery from magnitude measurements via convex programming. Comm. Pure Appl. Math. , 66:1241–1274, 2013. 24

    2013

  14. [22]

    Chen and E

    Y. Chen and E. J. Candès. Solving random quadratic syste ms of equations is nearly as easy as solving linear systems. Comm. Pure Appl. Math. , 70(5):822–883, 2017

    2017

  15. [23]

    Conca, D

    A. Conca, D. Edidin, M. Hering, and C. Vinzant. An algebr aic characterization of injectivity in phase retrieval. Applied and Computational Harmonic Analysis , 38(2):346–245, 2015

    2015

  16. [24]

    J. V. Corbett. The Pauli problem, state reconstruction and quantum-real numbers. Rep. Math. Phys. , 57:53–68, 2006

    2006

  17. [25]

    J. C. Dainty and J. R. Fienup. Image recovery: Theory and application. Phase retrieval and image reconstruction for astronomy, 21:231–275, Aug 1987

    1987

  18. [26]

    Daskalakis, D

    C. Daskalakis, D. Rohatgi, and E. Zampetakis. Constant -expansion suffices for compressed sensing with generative priors. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, De cember 6-12, 2020,...

    2020

  19. [27]

    Daude, M

    H. Daude, M. Mezard, T. Mora, and R. Zecchina. Pairs of sa t-assignments in random boolean formulae. Theoretical Computer Science , 393(1):260–279, 2008

    2008

  20. [28]

    Dhifallah, C

    O. Dhifallah, C. Thrampoulidis, and Y. M. Lu. Phase retr ieval via linear programming: Fundamental limits and algorithmic improvements. In 55th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2017, Monticello, IL, USA, October 3- 6, 2017, pages 10...

    2017

  21. [29]

    Dierolf, A

    M. Dierolf, A. Menzel, P. Thibault, P. Schneider, C. M. K ewish, A. Wepf, O. Bunk, and F. Pfeiffer. Ptychographic x-ray computed tomography at the nanoscale. Nature, 477(7314):436–439, 2010

    2010

  22. [30]

    Donoho, A

    D. Donoho, A. Maleki, and A. Montanari. Message-passin g algorithms for compressed sensing. Proc. National Academy of Sciences , 106(45):18914–18919, Nov. 2009

    2009

  23. [31]

    Duadi, O

    H. Duadi, O. Margalit, V. Mico, J. A. Rodrigo, T. Alieva, J. Garcia, and Z. Zalevsky. Digital holography and phase retrieval. In J. Rosen, editor, Source: Holography, Research and Technolo gies. InTech, 2011

    2011

  24. [32]

    Dudeja, M

    R. Dudeja, M. Bakhshizadeh, J. Ma, and A. Maleki. Analys is of spectral methods for phase retrieval with random orthogonal matrices. IEEE Trans. Inf. Theory , 66(8):5182–5203, 2020

    2020

  25. [33]

    Fannjiang and Z

    A. Fannjiang and Z. Zhang. Fixed point analysis of Dougl as-Rachford splitting for ptychography and phase retrieval. SIAM J. Imaging Sci. , 13(2):609–650, 2020

    2020

  26. [34]

    J. R. Fienup. Reconstruction of an object from the modul us of its Fourier transform. Optics letters , 3(1):27–29, Aug 1978

    1978

  27. [35]

    J. R. Fienup. Phase retrieval algorithms: a comparison . Appl. Opt. , 21(15):2758–2769, Aug 1982

    1982

  28. [36]

    D. Gabor. A new microscopic principle. Nature, 161:777778, 1948

    1948

  29. [37]

    Gabor, G

    D. Gabor, G. W. Stroke, D. Brumm, A. Funkhouser, and A. La beyrie. Reconstruction of phase objects by holography. Applied and Computational Harmonic Analysis , 208(516):1159–1162, 1965

    1965

  30. [38]

    Gamarnik

    D. Gamarnik. The overlap gap property: A topological ba rrier to optimizing over random structures. Proceedings of the National Academy of Sciences , 118(41), 2021

    2021

  31. [39]

    Gamarnik and M

    D. Gamarnik and M. Sudan. Limits of local algorithms ove r sparse random graphs. Proceedings of the 5th conference on innovations in theoretical computer scie nce, pages 369–376, 2014

    2014

  32. [40]

    Gamarnik and M

    D. Gamarnik and M. Sudan. Limits of local algorithms ove r sparse random graphs. Ann. Probab., 45(4):2353–2376, 2017

    2017

  33. [41]

    Gamarnik and M

    D. Gamarnik and M. Sudan. Performance of sequential loc al algorithms for the random NAE-K-SAT problem. SIAM Journal on Computing , 46(2):590–619, 2017

    2017

  34. [42]

    R. A. Gerchberg and W. O. Saxton. A practical algorithm f or the determination of phase from image and diffraction plane pictures. Optik, 35:237–246, 1972. 25

    1972

  35. [43]

    Goldstein and C

    T. Goldstein and C. Studer. PhaseMax: Convex phase retr ieval via basis pursuit. IEEE Trans. Inf. Theory, 64(4):2675–2689, 2018

    2018

  36. [44]

    Y. Gordon. On Milman’s inequality and random subspaces which escape through a mesh in Rn. Geometric Aspect of of functional analysis, Isr. Semin. 1986-8 7, Lect. Notes Math , 1317, 1988

    1986

  37. [45]

    Gross, F

    D. Gross, F. Krahmer, and R. Kueng. Improved recovery gu arantees for phase retrieval from coded diffraction patterns. Applied and Computational Harmonic Analysis , 42(1):37–64, 2017

    2017

  38. [46]

    J. Haah, A. W. Harrow, Z. Ji, X. Wu, and N. Yu. Sample-opti mal tomography of quantum states. IEEE Trans. Inf. Theory , 63(9):5628–5641, 2017

    2017

  39. [47]

    P. Hand. Phaselift is robust to a constant fraction of ar bitrary errors. Applied and Computational Harmonic Analysis , 42(3):550–362, 2017

    2017

  40. [48]

    P. Hand, O. Leong, and V. Voroninski. Phase retrieval un der a generative prior. In Advances in Neural Information Processing Systems 31: Annual Conference on Neur al Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada , pages 9154–9164, 2018

    2018

  41. [49]

    Hand and V

    P. Hand and V. Voroninski. An elementary proof of convex phase retrieval in the natural parameter space via the linear program phaseMax. 2016. available onli ne at http://arxiv.org/abs/1611. 03935

    2016

  42. [50]

    R. W. Harrison. Phase problem in crystallography. J. Opt. Soc. Am. A , 10(5):1046–1055, May 1993

    1993

  43. [51]

    Heinosaari, L

    T. Heinosaari, L. Mazzarella, and M. M. Wolf. Quantum to mography under prior information. Com- munications in Mathematical Physics , 318(2):355–374, 2013

    2013

  44. [52]

    N. Hurt. Phase Retrieval and Zero Crossings . Kluwer Academic Publishers, Norwell, MA, 1989

    1989

  45. [53]

    M. Iwen, A. Viswanathan, and Y. Wang. Robust sparse phas e retrieval made easy. Applied and Computational Harmonic Analysis , 42(1):135–142, 2017

    2017

  46. [54]

    Jaganathan, S

    K. Jaganathan, S. Oymak, and B. Hassibi. Sparse phase re trieval: Uniqueness guarantees and recovery algorithms. IEEE Trans. Signal Process. , 65(9):2402–2410, 2017

    2017

  47. [55]

    Jordan and A

    M. Jordan and A. G. Dimakis. Exactly computing the local lipschitz constant of relu networks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, v irtual, 2020

    2020

  48. [56]

    P. Jung, F. Krahmer, and D. Stroger. Blind demixing and d econvolution at near-optimal rate. IEEE Transactions on Information Theory , 44(2):704–727, 2017

    2017

  49. [57]

    M. V. Klibanov, P. E. Sacks, and A. V. Tikhonravov. The ph ase retrieval problem. Inverse Problems, 11(1):1, feb 1995

    1995

  50. [58]

    Kueng, H

    R. Kueng, H. Rauhut, and U. Terstiege. Low rank matrix re covery from rank one measurements. Applied and Computational Harmonic Analysis , 42(1):88–116, 2017

    2017

  51. [59]

    Q. Lei, A. Jalal, I. S. Dhillon, and A. G. Dimakis. Invert ing deep generative models, one layer at a time. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8- 14, 2019, Vancouver, ...

    2019

  52. [60]

    K.-C. Li. On principal hessian directions for data visu alization and dimension reduction: Another application of Stein’s lemma. J. Am. Stat. Assoc. , 87(420):1025–1039, 1992

    1992

  53. [61]

    X. Li, S. Ling, T. Strohmer, and K. Wei. Rapid, robust, an d reliable blind deconvolution via nonconvex optimization. Applied and computational harmonic analysis , 47(3):893–934, 2017. 26

    2017

  54. [62]

    Li and V

    X. Li and V. Voroninski. Sparse signal recovery from qua dratic measurements via convex programming. SIAM Journal on Mathematical Analysis , 45(5):3019–3033, 2013

    2013

  55. [63]

    Y. M. Lu and G. Li. Spectral initialization for nonconve x estimation: High-dimensional limit and phase transitions. In 2017 IEEE International Symposium on Information Theory, ISIT 2017, Aachen, Germany, June 25-30, 2017 , pages 3015–3019. IEEE, 2017

    2017

  56. [64]

    W. Luo, W. Alghamdi, and Y. M. Lu. Optimal spectral initi alization for signal recovery with applica- tions to phase retrieval. IEEE Trans. Signal Process. , 67(9):2347–2356, 2019

    2019

  57. [65]

    W. Luo, W. Alghamdi, Y. M. Lu, and G. Li. Phase transition s of spectral initialization for high- dimensional non-convex estimation. Information and Inference: A Journal of the IMA , 9(3):5077–541, 2020

    2020

  58. [66]

    J. Ma, R. Dudeja, J. Xu, A. Maleki, and X. Wang. Spectral m ethod for phase retrieval: An expectation propagation perspective. IEEE Trans. Inf. Theory , 67(2):1332–1355, 2021

    2021

  59. [67]

    Maillard, A

    A. Maillard, A. S. Bandeira, D. Belius, I. Dokmanic, and S. Nakajima. Injectivity of relu networks: perspectives from statistical physics. 2023. available on line at http://arxiv.org/abs/2302.14112

    2023 arXiv

  60. [68]

    Maillard, F

    A. Maillard, F. Krzakala, Y. M. Lu, and L. Zdeborová. Con struction of optimal spectral methods in phase retrieval. In Mathematical and Scientific Machine Learning, 16-19 August 2 021, Virtual Conference / Lausanne, Switzerland , volume 145 of Proceedings of Machine Learning Re...

    2021

  61. [69]

    Maillard, B

    A. Maillard, B. Loureiro, F. Krzakala, and L. Zdeborová . Phase retrieval in high dimensions: Statistical and computational phase transitions. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2 020, NeurIPS 202...

    2020

  62. [70]

    Marchesini

    S. Marchesini. Phase retrieval and saddle-point optim ization. JOSA A , 24(10):3289–3296, 2007

    2007

  63. [71]

    Marchesini, Y

    S. Marchesini, Y. C. Tu, and H. Wu. Alternating projecti on, ptychographic imaging and phase syn- chronization. 2014. available online at http://arxiv.org/abs/1402.0550

    2014 arXiv

  64. [72]

    Mezard, T

    M. Mezard, T. Mora, and R. Zecchina. Clustering of solut ions in the random satisfiability problem. Physical Review Letters , 94:197204, 2005

    2005

  65. [73]

    J. Miao, P. S. Charalambous, J. Kirz, and D. Sayre. Exten ding the methodology of x-ray crystallog- raphy to allow imaging of micrometre-sized non-crystallin e specimens. Nature, 400:342–344, 1999

    1999

  66. [74]

    J. Miao, T. Ishikawa, Q. Shen, and T. Earnest. Extending x-ray crystallography to allow the imaging of noncrystalline materials, cells and single protein comp lexes. Annu. Rev. Phys. Chem. , 59:387–410, 2008

    2008

  67. [75]

    R. P. Millane. Phase retrieval in crystallography and o ptics. J. Opt. Soc. Am. A , 7(3):394–411, Mar 1990

    1990

  68. [76]

    R. P. Millane. Recent advances in phase retrieval. In Image Reconstruction from Incomplete Data IV , volume 6316, page 63160E. International Society for Optics and Photonics, SPIE, 2006

    2006

  69. [77]

    D. L. Misell. A method for the solution of the phase probl em in electron microscopy. J. Phys. D: App. Phy., 6(1):L6–L9, 1973

    1973

  70. [78]

    Mondelli and A

    M. Mondelli and A. Montanari. Fundamental limits of wea k recovery with applications to phase retrieval. Found. Comput. Math. , 19(3):703–773, 2019

    2019

  71. [79]

    Montanari

    A. Montanari. Optimization of the Sherrington-Kirkpa trick hamiltonian. In 60th IEEE Annual Sympo- sium on Foundations of Computer Science, FOCS 2019, Baltimo re, Maryland, USA, November 9-12, 2019, pages 1417–1433. IEEE Computer Society, 2019. 27

    2019

  72. [80]

    Netrapalli, P

    P. Netrapalli, P. Jain, and S. Sanghavi. Phase retrieva l using alternating minimization. In Advances in Neural Information Processing Systems , pages 2796–2804, 2013

    2013

  73. [81]

    Netrapalli, P

    P. Netrapalli, P. Jain, and S. Sanghavi. Phase retrieva l using alternating minimization. IEEE Trans. Signal Process., 63(18):4814–4826, 2015

    2015

  74. [82]

    Ohlsson, A

    H. Ohlsson, A. Y. Yang, R. Dong, and S. S. Sastry. Compres sive phase retrieval from squared output measurements via semi-definite programming. In IF AC Proceedings, volume 45, pages 89–94, 2012

    2012

  75. [83]

    Rangan, P

    S. Rangan, P. Schniter, and A. K. Fletcher. Vector appro ximate message passing. In 2017 IEEE International Symposium on Information Theory, ISIT 2017, Aachen, Germany, June 25-30, 2017 , pages 1588–1592. IEEE, 2017

    2017

  76. [84]

    Rodenburg

    J.M. Rodenburg. Ptychography and related diffractive i maging methods. Advances in Imaging and Electron Physics, 150:87–184, 2008

    2008

  77. [85]

    Salehi, E

    F. Salehi, E. Abbasi, and B. Hassibi. A precise analysis of phasemax in phase retrieval. In 2018 IEEE International Symposium on Information Theory, ISIT 2018, Vail, CO , USA, June 17-22, 2018 , pages 976–980. IEEE, 2018

    2018

  78. [86]

    Schniter and S

    P. Schniter and S. Rangan. Compressive phase retrieval via generalized approximate message passing. IEEE Trans. Signal Process. , 63(4):1043–1055, 2015

    2015

  79. [87]

    Schniter, S

    P. Schniter, S. Rangan, and A. K. Fletcher. Vector appro ximate message passing for the generalized linear model. In 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, CA, USA, November 6-9, 2016 , pages 1525–1529. IEEE, 2016

    2016

  80. [88]

    Shechtman, Y

    Y. Shechtman, Y. C. Eldar, O. Cohen, H. N. Chapman, J. Mia o, and M. Segev. Phase retrieval with application to optical imaging: A contemporary overview. IEEE Signal Process. Mag. , 32(3):87–109, 2015

    2015

  81. [89]

    Soltanolkotabi

    M. Soltanolkotabi. Structured signal recovery from qu adratic measurements: Breaking sample com- plexity barriers via nonconvex optimization. IEEE Trans. Inf. Theory , 65(4):2374–2400, 2019

    2019

  82. [90]

    M. Stojnic. A framework for perfromance characterizat ion of LASSO algortihms. available online at http://arxiv.org/abs/1303.7291

    arXiv

  83. [91]

    M. Stojnic. Various thresholds for ℓ1-optimization in compressed sensing. available online at http:// arxiv.org/abs/0907.3666

    arXiv

  84. [92]

    M. Stojnic. Block-length dependent thresholds for ℓ2/ℓ1-optimization in block-sparse compressed sens- ing. ICASSP, IEEE International Conference on Acoustics, Signal and Speech Processing, pages 3918– 3921, 14-19 March 2010. Dallas, TX

    2010

  85. [93]

    M. Stojnic. ℓ1 optimization and its various thresholds in compressed sens ing. ICASSP, IEEE Inter- national Conference on Acoustics, Signal and Speech Proces sing, pages 3910–3913, 14-19 March 2010. Dallas, TX

    2010

  86. [94]

    M. Stojnic. Recovery thresholds for ℓ1 optimization in binary compressed sensing. ISIT, IEEE Inter- national Symposium on Information Theory , pages 1593 – 1597, 13-18 June 2010. Austin, TX

    2010

  87. [95]

    M. Stojnic. Towards improving ℓ1 optimization in compressed sensing. ICASSP, IEEE International Conference on Acoustics, Signal and Speech Processing , pages 3938–3941, 14-19 March 2010. Dallas, TX

    2010

  88. [96]

    M. Stojnic. Another look at the Gardner problem. 2013. a vailable online at http://arxiv.org/abs/ 1306.3979

    2013 arXiv

  89. [97]

    M. Stojnic. Regularly random duality. 2013. available online at http://arxiv.org/abs/1303.7295. 28

    2013 arXiv

  90. [98]

    M. Stojnic. Box constrained ℓ1 optimization in random linear systems – asymptotics. 2016. available online at http://arxiv.org/abs/1612.06835

    2016 arXiv

  91. [99]

    M. Stojnic. Fully bilinear generic and lifted random pr ocesses comparisons. 2016. available online at http://arxiv.org/abs/1612.08516

    2016 arXiv

  92. [100]

    M. Stojnic. Generic and lifted probabilistic compari sons – max replaces minmax. 2016. available online at http://arxiv.org/abs/1612.08506

    2016 arXiv

  93. [101]

    M. Stojnic. Fully lifted random duality theory. 2023. available online at http://arxiv.org/abs/ 2312.00070

    2023 arXiv

  94. [102]

    M. Stojnic. Deep relu networks – injectivity capacity upper bounds. 2024. available online at http:// arxiv.org/abs/2412.19677

    2024 arXiv

  95. [103]

    M. Stojnic. Injectivity capacity of relu gates. 2024. available online at http://arxiv.org/abs/2410. 20646

    2024

  96. [104]

    M. Stojnic. Phase transition of descending phase retrieval algorithms. 2025. available online at arxi v

    2025

  97. [105]

    Straziota and L

    D. Straziota and L. Saglietti. Isolating the hard core of phaseless inference: the Phase selection formulation. 2025. available online at http://arxiv.org/abs/2502.04282

    2025 arXiv

  98. [106]

    J. Sun, Q. Qu, and J. Wright. A geometric analysis of pha se retrieval. Found. Comput. Math. , 18(5):1131–1198, 2018

    2018

  99. [107]

    Takahashi and Y

    T. Takahashi and Y. Kabashima. Macroscopic analysis o f vector approximate message passing in a model-mismatched setting. IEEE Trans. Inf. Theory , 68(8):5579–5600, 2022

    2022

  100. [108]

    Y. S. Tan and R. Vershynin. Phase retrieval via randomi zed kaczmarz: Theoretical guarantees. Infor- mation and Inference: A Journal of the IMA , 8(1):97–123, 2019

    2019

  101. [109]

    Thibault, M

    P. Thibault, M. Dierolf, A. Menzel, O. Bunk, C. David, a nd F. Pfeffer. High-resolution scanning x-ray diffraction microscopy. Science, 322(5887):379–382, 2008

    2008

  102. [110]

    C. Vinzant. A small frame and a certificate of its inject ivity. In IEEE International Conference on Sampling Theory and Applications (SampTA) , pages 197–200, 2015

    2015

  103. [111]

    Waldspurger

    I. Waldspurger. Phase retrieval with random Gaussian sensing vectors by alternating projections. IEEE Trans. Inf. Theory , 64(5):3301–3312, 2018

    2018

  104. [112]

    Waldspurger, A

    I. Waldspurger, A. d’Aspremont, and S. Mallat. Phase r ecovery, maxcut and complex semidefinite programming. Math. Program., 149(1-2):47–81, 2015

    2015

  105. [113]

    A. Walther. The question of phase retrieval in optics. Optica Acta: International Journal of Optics , 10(1):41–49, 1963

    1963

  106. [114]

    G. Wang, G. B. Giannakis, and Y. C. Eldar. Solving syste ms of random quadratic equations via truncated amplitude flow. IEEE Trans. Inf. Theory , 64(2):773–794, 2018

    2018

  107. [115]

    K. Wei. Solving systems of phaseless equations via Kac zmarz methods: A proof of concept study. Inverse Problems, 31(12):125008, 2015

    2015

  108. [116]

    G. Yang, B. Dong, B. Gu, J. Zhuang, and O. K. Ersoy. Gerch berg-Saxton and Yang-Gu algorithms for phase retrieval in a nonunitary transform system: a compari son. Applied optics, 33(2):209–218, 1994

    1994

  109. [117]

    Z. Yuan, H. Wang, and Q. Wang. Phase retrieval via spars e Wirtinger flow. Journal of Computational and Applied Mathematics , 355:162–173, 2019. 29

    2019

Pith tools