{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:18:25Z","timestamp":1775179105135,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2022,8,1]]},"DOI":"10.1587\/transfun.2021eap1139","type":"journal-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T22:09:15Z","timestamp":1643062155000},"page":"1110-1120","source":"Crossref","is-referenced-by-count":12,"title":["Convergence Acceleration via Chebyshev Step: Plausible Interpretation of Deep-Unfolded Gradient Descent"],"prefix":"10.1587","volume":"E105.A","author":[{"given":"Satoshi","family":"TAKABE","sequence":"first","affiliation":[{"name":"Department of Mathematical and Computing Science, Tokyo Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadashi","family":"WADAYAMA","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Nagoya Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] K. Gregor and Y. LeCun, \u201cLearning fast approximations of sparse coding,\u201d Proc. 27th International Conference on International Conference on Machine Learning, pp.399-406, Omnipress, 2010."},{"key":"2","unstructured":"[2] J.R. Hershey, J.L. Roux, and F. Weninger, \u201cDeep unfolding: Model-based inspiration of novel deep architectures,\u201d arXiv preprint arXiv:1409.2574, 2014. 10.48550\/arXiv.1409.2574"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] P. Sprechmann, A.M. Bronstein, and G. Sapiro, \u201cLearning efficient sparse and low rank models,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.37, no.9, pp.1821-1833, 2015. 10.1109\/tpami.2015.2392779","DOI":"10.1109\/TPAMI.2015.2392779"},{"key":"4","unstructured":"[4] B. Xin, Y. Wang, W. Gao, D. Wipf, and B. Wang, \u201cMaximal sparsity with deep networks?,\u201d Advances in Neural Information Processing Systems, pp.4340-4348, 2016."},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] M. Borgerding, P. Schniter, and S. Rangan, \u201cAMP-inspired deep networks for sparse linear inverse problems,\u201d IEEE Trans. Signal Process., vol.65, no.16, pp.4293-4308, 2017. 10.1109\/tsp.2017.2708040","DOI":"10.1109\/TSP.2017.2708040"},{"key":"6","unstructured":"[6] S. Wu, A. Dimakis, S. Sanghavi, F. Yu, D. Holtmann-Rice, D. Storcheus, A. Rostamizadeh, and S. Kumar, \u201cLearning a compressed sensing measurement matrix via gradient unrolling,\u201d Proc. 36th International Conference on Machine Learning, K. Chaudhuri and R. Salakhutdinov, eds., Proc. Machine Learning Research, vol.97, Long Beach, California, USA, pp.6828-6839, PMLR, June 2019."},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] D. Ito, S. Takabe, and T. Wadayama, \u201cTrainable ISTA for sparse signal recovery,\u201d IEEE Trans. Signal Process., vol.67, no.12, pp.3113-3125, 2019. 10.1109\/tsp.2019.2912879","DOI":"10.1109\/TSP.2019.2912879"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] S. Takabe, T. Wadayama, and Y.C. Eldar, \u201cComplex trainable ista for linear and nonlinear inverse problems,\u201d ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5020-5024, IEEE, 2020. 10.1109\/icassp40776.2020.9053161","DOI":"10.1109\/ICASSP40776.2020.9053161"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] W. Shi, F. Jiang, S. Zhang, and D. Zhao, \u201cDeep networks for compressed image sensing,\u201d 2017 IEEE International Conference on Multimedia and Expo (ICME), pp.877-882, IEEE, 2017. 10.1109\/icme.2017.8019428","DOI":"10.1109\/ICME.2017.8019428"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] K.H. Jin, M.T. McCann, E. Froustey, and M. Unser, \u201cDeep convolutional neural network for inverse problems in imaging,\u201d IEEE Trans. Image Process., vol.26, no.9, pp.4509-4522, 2017. 10.1109\/tip.2017.2713099","DOI":"10.1109\/TIP.2017.2713099"},{"key":"11","unstructured":"[11] M. Mardani, Q. Sun, D. Donoho, V. Papyan, H. Monajemi, S. Vasanawala, and J. Pauly, \u201cNeural proximal gradient descent for compressive imaging,\u201d Advances in Neural Information Processing Systems, pp.9573-9583, 2018."},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] M. Kellman, E. Bostan, N. Repina, and L. Waller, \u201cPhysics-based learned design: Optimized coded-illumination for quantitative phase imaging,\u201d IEEE Trans. Computat. Imag., vol.5, no.3, pp.344-353, 2019. 10.1109\/tci.2019.2905434","DOI":"10.1109\/TCI.2019.2905434"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] E. Nachmani, Y. Be'ery, and D. Burshtein, \u201cLearning to decode linear codes using deep learning,\u201d 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp.341-346, IEEE, 2016. 10.1109\/allerton.2016.7852251","DOI":"10.1109\/ALLERTON.2016.7852251"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] N. Samuel, T. Diskin, and A. Wiesel, \u201cDeep MIMO detection,\u201d 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), pp.1-5, IEEE, 2017. 10.1109\/spawc.2017.8227772","DOI":"10.1109\/SPAWC.2017.8227772"},{"key":"15","doi-asserted-by":"crossref","unstructured":"[15] H. He, C.K. Wen, S. Jin, and G.Y. Li, \u201cA model-driven deep learning network for MIMO detection,\u201d 2018 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp.584-588, IEEE, 2018. 10.1109\/globalsip.2018.8646357","DOI":"10.1109\/GlobalSIP.2018.8646357"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] S. Takabe, M. Imanishi, T. Wadayama, R. Hayakawa, and K. Hayashi, \u201cTrainable projected gradient detector for massive overloaded MIMO channels: Data-driven tuning approach,\u201d IEEE Access, vol.7, pp.93326-93338, 2019. 10.1109\/access.2019.2927997","DOI":"10.1109\/ACCESS.2019.2927997"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] M. Yao, J. Dang, Z. Zhang, and L. Wu, \u201cSURE-TISTA: A signal recovery network for compressed sensing,\u201d ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.3832-3836, IEEE, 2019. 10.1109\/icassp.2019.8683182","DOI":"10.1109\/ICASSP.2019.8683182"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] T. Wadayama and S. Takabe, \u201cDeep learning-aided trainable projected gradient decoding for LDPC codes,\u201d IEEE International Symposium on Information Theory, ISIT 2019, Paris, France, pp.2444-2448, July 2019. 10.1109\/isit.2019.8849215","DOI":"10.1109\/ISIT.2019.8849215"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] S. Takabe and T. Wadayama, \u201cDeep unfolded multicast beamforming,\u201d arXiv preprint arXiv:2004.09345, 2020. 10.48550\/arXiv.2004.09345","DOI":"10.1109\/GLOBECOM42002.2020.9322114"},{"key":"20","doi-asserted-by":"publisher","unstructured":"[20] M. Kishida, M. Ogura, Y. Yoshida, and T. Wadayama, \u201cDeep learning-based average consensus,\u201d IEEE Access, vol.8, pp.142404-142412, 2020. 10.1109\/access.2020.3014148","DOI":"10.1109\/ACCESS.2020.3014148"},{"key":"21","unstructured":"[21] X. Chen, J. Liu, Z. Wang, and W. Yin, \u201cTheoretical linear convergence of unfolded ISTA and its practical weights and thresholds,\u201d Advances in Neural Information Processing Systems, pp.9061-9071, 2018."},{"key":"22","unstructured":"[22] J. Liu, X. Chen, Z. Wang, and W. Yin, \u201cALISTA: Analytic weights are as good as learned weights in LISTA,\u201d International Conference on Learning Representations, 2019."},{"key":"23","unstructured":"[23] M. Mardani, Q. Sun, V. Papyan, S. Vasanawala, J. Pauly, and D. Donoho, \u201cDegrees of freedom analysis of unrolled neural networks,\u201d arXiv preprint arXiv:1906.03742, 2019. 10.48550\/arXiv.1906.03742"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] A. Balatsoukas-Stimming and C. Studer, \u201cDeep unfolding for communications systems: A survey and some new directions,\u201d 2019 IEEE International Workshop on Signal Processing Systems (SiPS), pp.266-271, 2019. 10.1109\/sips47522.2019.9020494","DOI":"10.1109\/SiPS47522.2019.9020494"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] V. Monga, Y. Li, and Y.C. Eldar, \u201cAlgorithm unrolling: Interpretable, efficient deep learning for signal and image processing,\u201d IEEE Signal Process. Mag., vol.38, no.2, pp.18-44, March 2021. 10.1109\/msp.2020.3016905","DOI":"10.1109\/MSP.2020.3016905"},{"key":"26","unstructured":"[26] Z.C. Lipton, \u201cThe mythos of model interpretability,\u201d arXiv preprint arXiv:1606.03490, 2016. 10.48550\/arXiv.1606.03490"},{"key":"27","doi-asserted-by":"publisher","unstructured":"[27] J. Yi, L. Chai, and J. Zhang, \u201cAverage consensus by graph filtering: New approach, explicit convergence rate, and optimal design,\u201d IEEE Trans. Autom. Control, vol.65, no.1, pp.191-206, 2020. 10.1109\/tac.2019.2907410","DOI":"10.1109\/TAC.2019.2907410"},{"key":"28","unstructured":"[28] D.P. Kingma and J. Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014. 10.48550\/arXiv.1412.6980"},{"key":"29","unstructured":"[29] D.P. Bertsekas, Nonlinear Programming, Athena Scientific, 1995."},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, \u201cLearning representations by back-propagating errors,\u201d Nature, vol.323, no.6088, pp.533-536, Oct. 1986. 10.1038\/323533a0","DOI":"10.1038\/323533a0"},{"key":"31","unstructured":"[31] Y. Nesterov, \u201cIntroductory lectures on convex programming volume I: Basic course,\u201d Lecture Notes, vol.3, no.4, p.5, 1998."},{"key":"32","doi-asserted-by":"publisher","unstructured":"[32] T. Wadayama and S. Takabe, \u201cChebyshev periodical successive over-relaxation for accelerating fixed-point iterations,\u201d IEEE Signal Process. Lett., vol.28, pp.907-911, 2021. 10.1109\/lsp.2021.3073620","DOI":"10.1109\/LSP.2021.3073620"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[33] L. Hogben, Handbook of Linear Algebra, Chapman and Hall\/CRC, 2013. 10.1201\/b16113","DOI":"10.1201\/b16113"},{"key":"34","doi-asserted-by":"crossref","unstructured":"[34] J.C. Mason and D.C. Handscomb, Chebyshev Polynomial, CRC Press, 2003.","DOI":"10.1201\/9781420036114"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] C. Fox, \u201cPolynomial accelerated MCMC and other sampling algorithms inspired by computational optimization,\u201d Springer Proceedings in Mathematics and Statistics, vol.65, pp.349-366, 2013. 10.1007\/978-3-642-41095-6_15","DOI":"10.1007\/978-3-642-41095-6_15"},{"key":"36","unstructured":"[36] P. Ablin, T. Moreau, M. Massias, and A. Gramfort, \u201cLearning step sizes for unfolded sparse coding,\u201d in Advances in Neural Information Processing Systems 32, pp.13100-13110, Curran Associates, 2019."},{"key":"37","doi-asserted-by":"publisher","unstructured":"[37] B.T. Polyak, \u201cSome methods of speeding up the convergence of iteration methods,\u201d USSR Computational Mathematics and Mathematical Physics, vol.4, no.5, pp.1-17, 1964. 10.1016\/0041-5553(64)90137-5","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"38","doi-asserted-by":"publisher","unstructured":"[38] G.H. Golub and M.D. Kent, \u201cEstimates of eigenvalues for iterative methods,\u201d Math. Comput., vol.53, no.188, pp.619-626, 1989. 10.1090\/s0025-5718-1989-0979938-6","DOI":"10.1090\/S0025-5718-1989-0979938-6"}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E105.A\/8\/E105.A_2021EAP1139\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,6]],"date-time":"2022-08-06T03:28:47Z","timestamp":1659756527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E105.A\/8\/E105.A_2021EAP1139\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,1]]},"references-count":38,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2021eap1139","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,1]]},"article-number":"2021EAP1139"}}