Learning to Optimize: Training Deep Neural Networks for Interference Management

Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as communications, radar, filter design, and speech and image analytics, just to name a few. However, optimizat...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on signal processing Vol. 66; no. 20; pp. 5438 - 5453
Main Authors:	Sun, Haoran, Chen, Xiangyi, Shi, Qingjiang, Hong, Mingyi, Fu, Xiao, Sidiropoulos, Nicholas D.
Format:	Journal Article
Language:	English
Published:	New York IEEE 15.10.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Approximation algorithms Artificial neural networks Computing time deep neural networks Design analysis Filter design (mathematics) Interference interference management Machine learning algorithms Management Mapping Neural networks Optimization Optimization algorithms Optimization algorithms approximation Radar imaging Signal processing Signal processing algorithms Task analysis Wireless communication WMMSE algorithm
ISSN:	1053-587X, 1941-0476
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as communications, radar, filter design, and speech and image analytics, just to name a few. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. In this paper, we aim at providing a new learning-based perspective to address this challenging issue. The key idea is to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it. If the nonlinear mapping can be learned accurately by a DNN of moderate size, then SP tasks can be performed effectively-since passing the input through a DNN only requires a small number of simple operations. In our paper, we first identify a class of optimization algorithms that can be accurately approximated by a fully connected DNN. Second, to demonstrate the effectiveness of the proposed approach, we apply it to approximate a popular interference management algorithm, namely, the WMMSE algorithm. Extensive experiments using both synthetically generated wireless channel data and real DSL channel data have been conducted. It is shown that, in practice, only a small network is sufficient to obtain high approximation accuracy, and DNNs can achieve orders of magnitude speedup in computational time compared to the state-of-the-art interference management algorithm.
AbstractList	Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large variety of SP applications such as communications, radar, filter design, and speech and image analytics, just to name a few. However, optimization algorithms often entail considerable complexity, which creates a serious gap between theoretical design/analysis and real-time processing. In this paper, we aim at providing a new learning-based perspective to address this challenging issue. The key idea is to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it. If the nonlinear mapping can be learned accurately by a DNN of moderate size, then SP tasks can be performed effectively-since passing the input through a DNN only requires a small number of simple operations. In our paper, we first identify a class of optimization algorithms that can be accurately approximated by a fully connected DNN. Second, to demonstrate the effectiveness of the proposed approach, we apply it to approximate a popular interference management algorithm, namely, the WMMSE algorithm. Extensive experiments using both synthetically generated wireless channel data and real DSL channel data have been conducted. It is shown that, in practice, only a small network is sufficient to obtain high approximation accuracy, and DNNs can achieve orders of magnitude speedup in computational time compared to the state-of-the-art interference management algorithm.
Author	Sun, Haoran Sidiropoulos, Nicholas D. Hong, Mingyi Chen, Xiangyi Shi, Qingjiang Fu, Xiao
Author_xml	– sequence: 1 givenname: Haoran orcidid: 0000-0002-6266-123X surname: Sun fullname: Sun, Haoran email: sun00111@umn.edu organization: Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA – sequence: 2 givenname: Xiangyi surname: Chen fullname: Chen, Xiangyi email: chen5719@umn.edu organization: Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA – sequence: 3 givenname: Qingjiang orcidid: 0000-0003-0507-9080 surname: Shi fullname: Shi, Qingjiang email: qing.j.shi@gmail.com organization: School of Software Engineering, Tongji University, Shanghai, China – sequence: 4 givenname: Mingyi orcidid: 0000-0003-1263-9365 surname: Hong fullname: Hong, Mingyi email: mhong@umn.edu organization: Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN, USA – sequence: 5 givenname: Xiao orcidid: 0000-0003-4847-9586 surname: Fu fullname: Fu, Xiao email: xiao.fu@oregonstate.edu organization: School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, OR, USA – sequence: 6 givenname: Nicholas D. orcidid: 0000-0002-3385-7911 surname: Sidiropoulos fullname: Sidiropoulos, Nicholas D. email: nikos@virginia.edu organization: Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA, USA
BookMark	eNp9kM1LAzEQxYMo2FbvgpcFz1vztdmsN6lfhWoFK3gLcXdSUttkzaaI_vWmtnjw4GF4w_B-M8zro33nHSB0QvCQEFydz54ehxQTOaRSCCbpHuqRipMc81Lspx4XLC9k-XKI-l23wJhwXokemk5AB2fdPIs-m7bRruwXXGSzoO3P9AqgzR5gHfQySfzw4a3LjA_Z2EUIBgK4GrJ77fQcVuDiETowetnB8U4H6Pnmeja6yyfT2_HocpLXjLGYl5wbRivaYFFXPJXGRDei1LyuWSmxbgwIagwFIxtCCkmBlEQI2cBrTQvDBuhsu7cN_n0NXVQLvw4unVSUbKwlKXByia2rDr7rAhhV26ij9S6mB5eKYLUJT6Xw1CY8tQsvgfgP2Aa70uHzP-R0i1gA-LVLzrngkn0DoBR8Hg
CODEN	ITPRED
CitedBy_id	crossref_primary_10_1109_TVT_2020_2981409 crossref_primary_10_1109_JSAC_2021_3087240 crossref_primary_10_1109_TWC_2024_3442091 crossref_primary_10_32604_cmc_2024_046403 crossref_primary_10_3390_signals6010003 crossref_primary_10_1002_ett_4579 crossref_primary_10_1109_TCOMM_2024_3385919 crossref_primary_10_1109_TCOMM_2024_3486982 crossref_primary_10_1109_LWC_2022_3216330 crossref_primary_10_3390_fi16110408 crossref_primary_10_1109_JIOT_2024_3423008 crossref_primary_10_1109_TVT_2021_3113051 crossref_primary_10_1007_s40747_023_01148_7 crossref_primary_10_1109_TWC_2020_2977340 crossref_primary_10_1109_TSP_2021_3071210 crossref_primary_10_1109_TWC_2023_3309900 crossref_primary_10_1016_j_phycom_2021_101294 crossref_primary_10_1016_j_phycom_2021_101292 crossref_primary_10_1016_j_sigpro_2022_108685 crossref_primary_10_1109_ACCESS_2025_3537160 crossref_primary_10_1109_ACCESS_2022_3224808 crossref_primary_10_1109_ACCESS_2023_3316605 crossref_primary_10_1109_TWC_2025_3530003 crossref_primary_10_1016_j_apenergy_2023_121234 crossref_primary_10_1109_COMST_2023_3330910 crossref_primary_10_1109_TCOMM_2022_3227932 crossref_primary_10_1109_ACCESS_2020_2978935 crossref_primary_10_1109_ACCESS_2019_2963468 crossref_primary_10_1109_TWC_2024_3472612 crossref_primary_10_1016_j_iot_2022_100512 crossref_primary_10_1109_TVT_2024_3369748 crossref_primary_10_1109_TVT_2024_3497603 crossref_primary_10_1109_JIOT_2023_3275818 crossref_primary_10_1109_TWC_2025_3541144 crossref_primary_10_1109_TVT_2021_3125499 crossref_primary_10_1109_MWC_006_2400131 crossref_primary_10_1109_JIOT_2024_3368516 crossref_primary_10_1109_COMST_2023_3249835 crossref_primary_10_1016_j_comcom_2023_03_004 crossref_primary_10_1109_TVT_2021_3068368 crossref_primary_10_1109_ACCESS_2024_3399563 crossref_primary_10_1109_TSP_2020_3035832 crossref_primary_10_1109_TMC_2021_3125793 crossref_primary_10_1109_JSAC_2024_3443759 crossref_primary_10_1109_TWC_2022_3166964 crossref_primary_10_1109_TCOMM_2022_3199477 crossref_primary_10_1109_TCOMM_2022_3158646 crossref_primary_10_1109_TSP_2020_2988255 crossref_primary_10_1016_j_phycom_2021_101476 crossref_primary_10_1109_JIOT_2021_3072840 crossref_primary_10_1109_LCOMM_2019_2936473 crossref_primary_10_1109_LCOMM_2020_3005947 crossref_primary_10_1109_ACCESS_2021_3122331 crossref_primary_10_1049_cmu2_12669 crossref_primary_10_1109_TWC_2024_3437668 crossref_primary_10_1109_ACCESS_2024_3423840 crossref_primary_10_1109_JPHOT_2019_2938231 crossref_primary_10_1109_JIOT_2024_3368692 crossref_primary_10_1109_TCCN_2019_2941191 crossref_primary_10_3389_fnhum_2025_1583342 crossref_primary_10_1109_TPWRS_2019_2909150 crossref_primary_10_1109_TCOMM_2022_3199018 crossref_primary_10_1109_LCOMM_2021_3063707 crossref_primary_10_1109_TWC_2021_3068578 crossref_primary_10_1109_MCOM_001_1900199 crossref_primary_10_1108_BIJ_06_2022_0401 crossref_primary_10_1109_MSP_2020_2996545 crossref_primary_10_4218_etrij_2022_0462 crossref_primary_10_1109_TVT_2022_3201961 crossref_primary_10_1016_j_comnet_2023_109581 crossref_primary_10_3390_app11052163 crossref_primary_10_1109_TVT_2022_3192833 crossref_primary_10_1109_TCOMM_2019_2947514 crossref_primary_10_1109_TSP_2022_3143372 crossref_primary_10_1109_TWC_2020_3033334 crossref_primary_10_1109_TNSE_2022_3163274 crossref_primary_10_1109_JPROC_2024_3409428 crossref_primary_10_1109_MWC_003_21003437 crossref_primary_10_1109_JSAC_2021_3087233 crossref_primary_10_1016_j_engappai_2021_104451 crossref_primary_10_1016_j_phycom_2021_101364 crossref_primary_10_1109_TMC_2025_3542434 crossref_primary_10_1109_TVT_2020_3028010 crossref_primary_10_1109_JPROC_2019_2941458 crossref_primary_10_1109_JSAC_2019_2904352 crossref_primary_10_1109_TVT_2022_3188104 crossref_primary_10_1109_TSP_2023_3238275 crossref_primary_10_3390_electronics13050872 crossref_primary_10_1109_TWC_2020_3043009 crossref_primary_10_1109_JIOT_2023_3263756 crossref_primary_10_1109_OJCOMS_2025_3549434 crossref_primary_10_1002_ett_4324 crossref_primary_10_1109_ACCESS_2021_3094976 crossref_primary_10_1109_TCCN_2019_2945774 crossref_primary_10_1109_TVT_2022_3213368 crossref_primary_10_1109_LWC_2024_3362050 crossref_primary_10_3390_app10134622 crossref_primary_10_1109_ACCESS_2022_3195898 crossref_primary_10_1002_itl2_317 crossref_primary_10_1109_TCOMM_2023_3282220 crossref_primary_10_1109_MCOM_001_2000367 crossref_primary_10_1109_TVT_2023_3302814 crossref_primary_10_1109_TVT_2024_3375020 crossref_primary_10_1007_s10845_023_02261_7 crossref_primary_10_1109_TWC_2022_3218579 crossref_primary_10_1109_TWC_2024_3361174 crossref_primary_10_1109_TVT_2023_3250963 crossref_primary_10_1109_TSP_2022_3207269 crossref_primary_10_1109_TGCN_2021_3058657 crossref_primary_10_3390_app9173470 crossref_primary_10_1016_j_compchemeng_2024_108859 crossref_primary_10_1016_j_phycom_2025_102630 crossref_primary_10_1109_LSP_2023_3289438 crossref_primary_10_1109_MNET_105_2100450 crossref_primary_10_1049_cmu2_70005 crossref_primary_10_1109_ACCESS_2025_3573096 crossref_primary_10_1109_ACCESS_2018_2890441 crossref_primary_10_1109_TWC_2022_3195352 crossref_primary_10_1109_TVT_2022_3187440 crossref_primary_10_1109_TPWRS_2021_3127189 crossref_primary_10_1007_s00521_020_05142_9 crossref_primary_10_1109_TWC_2020_2996368 crossref_primary_10_1007_s11432_022_3566_4 crossref_primary_10_1109_JIOT_2024_3359674 crossref_primary_10_1109_TVT_2022_3151471 crossref_primary_10_1007_s11227_022_04656_4 crossref_primary_10_1109_TCCN_2022_3222847 crossref_primary_10_1109_TWC_2020_3001736 crossref_primary_10_1109_TWC_2020_3041319 crossref_primary_10_1109_JIOT_2021_3113895 crossref_primary_10_1109_TNSE_2020_3004333 crossref_primary_10_1109_JSAC_2021_3126076 crossref_primary_10_1109_TWC_2023_3271521 crossref_primary_10_1109_TCCN_2021_3061464 crossref_primary_10_1109_TVT_2021_3057648 crossref_primary_10_1109_TWC_2021_3065029 crossref_primary_10_1109_LCOMM_2020_3027994 crossref_primary_10_3390_biomimetics8020241 crossref_primary_10_1109_TWC_2021_3138733 crossref_primary_10_3390_en12224300 crossref_primary_10_1049_iet_com_2019_1211 crossref_primary_10_1109_TCOMM_2022_3228611 crossref_primary_10_1109_TMLCN_2025_3562808 crossref_primary_10_1109_JIOT_2024_3369687 crossref_primary_10_1109_JSAC_2019_2933890 crossref_primary_10_1109_ACCESS_2021_3097243 crossref_primary_10_1109_TVT_2021_3082776 crossref_primary_10_1109_JSAC_2021_3118430 crossref_primary_10_1109_LCOMM_2020_3041510 crossref_primary_10_1109_ACCESS_2020_3040133 crossref_primary_10_1109_MNET_003_2200275 crossref_primary_10_1109_TSP_2020_3048232 crossref_primary_10_1109_TCCN_2023_3254515 crossref_primary_10_1109_TVT_2024_3515056 crossref_primary_10_1109_TWC_2020_3022705 crossref_primary_10_1109_TWC_2022_3193138 crossref_primary_10_1109_TVT_2018_2882635 crossref_primary_10_3390_s19153423 crossref_primary_10_1109_TWC_2022_3217176 crossref_primary_10_1109_MNET_001_1900517 crossref_primary_10_1109_TSP_2019_2908906 crossref_primary_10_1109_JSAC_2021_3126050 crossref_primary_10_1109_TCOMM_2025_3534565 crossref_primary_10_1109_ACCESS_2022_3208284 crossref_primary_10_1109_TWC_2021_3053354 crossref_primary_10_3390_app10103634 crossref_primary_10_1109_TCCN_2020_3013257 crossref_primary_10_3390_electronics11182842 crossref_primary_10_1109_JSAC_2019_2933969 crossref_primary_10_1109_TWC_2021_3088224 crossref_primary_10_1109_LCOMM_2024_3474251 crossref_primary_10_1109_TWC_2019_2919611 crossref_primary_10_1016_j_phycom_2021_101402 crossref_primary_10_3390_network3010003 crossref_primary_10_1109_TWC_2023_3279442 crossref_primary_10_1109_TSP_2021_3079807 crossref_primary_10_1109_TSP_2021_3096466 crossref_primary_10_1002_aic_18338 crossref_primary_10_1007_s42484_020_00014_w crossref_primary_10_1109_LWC_2022_3202904 crossref_primary_10_1007_s11432_024_4205_8 crossref_primary_10_1109_JSYST_2018_2870483 crossref_primary_10_1109_TCOMM_2021_3133939 crossref_primary_10_1109_TCOMM_2023_3251995 crossref_primary_10_1016_j_eng_2025_07_032 crossref_primary_10_1007_s11036_022_02013_6 crossref_primary_10_1109_TCOMM_2023_3310537 crossref_primary_10_1109_TVT_2023_3237551 crossref_primary_10_1109_LCOMM_2024_3503656 crossref_primary_10_1109_TCCN_2022_3228584 crossref_primary_10_1109_ACCESS_2021_3079639 crossref_primary_10_1109_LCOMM_2022_3161712 crossref_primary_10_3390_electronics10030318 crossref_primary_10_1109_JSAC_2019_2933973 crossref_primary_10_1109_MWC_003_2200382 crossref_primary_10_1109_JSAC_2022_3143215 crossref_primary_10_1109_ACCESS_2021_3121724 crossref_primary_10_1109_LCOMM_2020_2965532 crossref_primary_10_1109_TSP_2023_3244104 crossref_primary_10_1109_TVT_2020_2965959 crossref_primary_10_1109_TNNLS_2021_3054778 crossref_primary_10_1109_LWC_2022_3186160 crossref_primary_10_1109_JSAC_2023_3242716 crossref_primary_10_1109_TWC_2022_3180035 crossref_primary_10_1109_TWC_2023_3325735 crossref_primary_10_1109_ACCESS_2018_2887308 crossref_primary_10_1109_TSP_2023_3334396 crossref_primary_10_1109_ACCESS_2021_3060480 crossref_primary_10_1109_TWC_2024_3396798 crossref_primary_10_1109_ACCESS_2024_3450578 crossref_primary_10_1109_TWC_2021_3123620 crossref_primary_10_1109_JSAC_2020_3036965 crossref_primary_10_1038_s41598_023_41700_6 crossref_primary_10_1109_ACCESS_2021_3109948 crossref_primary_10_1109_TSP_2022_3163626 crossref_primary_10_1109_LWC_2022_3206096 crossref_primary_10_1109_TWC_2023_3323207 crossref_primary_10_1109_TCOMM_2020_2983036 crossref_primary_10_1109_TNSM_2021_3049824 crossref_primary_10_1109_TVT_2019_2949122 crossref_primary_10_1109_TWC_2022_3204794 crossref_primary_10_1109_TWC_2020_3040983 crossref_primary_10_1109_TWC_2022_3219840 crossref_primary_10_1109_TWC_2023_3314930 crossref_primary_10_1109_JPROC_2019_2957798 crossref_primary_10_1016_j_ifacol_2025_07_051 crossref_primary_10_1109_LWC_2025_3582828 crossref_primary_10_1109_ACCESS_2020_2978253 crossref_primary_10_3389_fdata_2022_787421 crossref_primary_10_1109_TCOMM_2021_3129199 crossref_primary_10_1109_ACCESS_2019_2937982 crossref_primary_10_1109_TVT_2023_3246982 crossref_primary_10_1109_TWC_2021_3107452 crossref_primary_10_1109_TCCN_2023_3287240 crossref_primary_10_1109_TNSE_2025_3539824 crossref_primary_10_1109_JPROC_2021_3053601 crossref_primary_10_1109_TWC_2025_3560116 crossref_primary_10_1109_ACCESS_2023_3342320 crossref_primary_10_1007_s10489_024_05391_4 crossref_primary_10_1109_TVT_2021_3055205 crossref_primary_10_1016_j_adhoc_2023_103208 crossref_primary_10_1109_ACCESS_2024_3437670 crossref_primary_10_1109_ACCESS_2023_3345831 crossref_primary_10_1109_TNSE_2023_3335973 crossref_primary_10_1109_TCOMM_2024_3405372 crossref_primary_10_1109_JSAC_2020_3000835 crossref_primary_10_1109_TWC_2022_3192203 crossref_primary_10_1109_ACCESS_2024_3462987 crossref_primary_10_1109_TWC_2019_2947591 crossref_primary_10_1109_TWC_2022_3230662 crossref_primary_10_1109_TWC_2022_3179352 crossref_primary_10_1016_j_phycom_2023_102158 crossref_primary_10_1109_JIOT_2020_3023111 crossref_primary_10_1109_ACCESS_2020_2971698 crossref_primary_10_1051_shsconf_202214403016 crossref_primary_10_1080_00207217_2020_1843715 crossref_primary_10_1109_TWC_2020_3031920 crossref_primary_10_3390_math12111755 crossref_primary_10_1016_j_phycom_2025_102620 crossref_primary_10_1109_COMST_2020_3024783 crossref_primary_10_1109_TVT_2020_2972596 crossref_primary_10_1109_TWC_2022_3181219 crossref_primary_10_3390_electronics14132734 crossref_primary_10_1016_j_aej_2025_08_032 crossref_primary_10_1109_TCOMM_2020_2983142 crossref_primary_10_1109_ACCESS_2023_3288698 crossref_primary_10_1109_JSAC_2020_3000812 crossref_primary_10_1109_MWC_003_2200239 crossref_primary_10_1109_TCCN_2024_3510577 crossref_primary_10_1109_TVT_2020_3037060 crossref_primary_10_1016_j_adhoc_2024_103509 crossref_primary_10_1109_ACCESS_2021_3107430 crossref_primary_10_1109_TVT_2019_2953724 crossref_primary_10_1109_TVT_2021_3106398 crossref_primary_10_1109_TWC_2021_3089701 crossref_primary_10_1109_ACCESS_2020_3033333 crossref_primary_10_1002_ett_70027 crossref_primary_10_1109_TWC_2023_3253126 crossref_primary_10_1109_ACCESS_2021_3117451 crossref_primary_10_1109_TCOMM_2023_3300331 crossref_primary_10_1109_ACCESS_2021_3104277 crossref_primary_10_1109_TSP_2025_3574005 crossref_primary_10_1109_TWC_2020_3030973 crossref_primary_10_1109_LWC_2023_3257128 crossref_primary_10_1109_TWC_2021_3094162 crossref_primary_10_1109_TWC_2023_3269815 crossref_primary_10_1016_j_phycom_2024_102429 crossref_primary_10_1109_ACCESS_2022_3159679 crossref_primary_10_1109_ACCESS_2022_3182552 crossref_primary_10_1109_TCOMM_2020_2998858 crossref_primary_10_1109_TSTE_2021_3086846 crossref_primary_10_1109_JIOT_2025_3559063 crossref_primary_10_1109_ACCESS_2020_2992629 crossref_primary_10_1109_TCOMM_2019_2924010 crossref_primary_10_1016_j_icte_2022_08_009 crossref_primary_10_1109_TWC_2020_2981320 crossref_primary_10_1109_LSP_2022_3143771 crossref_primary_10_1109_TMC_2025_3563892 crossref_primary_10_1109_ACCESS_2024_3457805 crossref_primary_10_1049_cit2_12114 crossref_primary_10_1007_s00500_023_08623_w crossref_primary_10_1109_TWC_2024_3509276 crossref_primary_10_1109_TVT_2021_3050104 crossref_primary_10_1109_TWC_2023_3336911 crossref_primary_10_1109_ACCESS_2023_3326842 crossref_primary_10_1007_s11432_023_3880_y crossref_primary_10_1109_LWC_2023_3329036 crossref_primary_10_1109_TAES_2023_3334216 crossref_primary_10_1177_15501329221104330 crossref_primary_10_1109_COMST_2024_3450292 crossref_primary_10_1109_TWC_2021_3071480 crossref_primary_10_1109_JPROC_2024_3437730 crossref_primary_10_1109_TVT_2024_3442167 crossref_primary_10_1109_TWC_2023_3287885 crossref_primary_10_1109_TVT_2021_3064868 crossref_primary_10_1016_j_phycom_2019_100941 crossref_primary_10_1016_j_neucom_2020_06_137 crossref_primary_10_1109_ACCESS_2019_2954467 crossref_primary_10_1109_COMST_2021_3135829 crossref_primary_10_1109_TNET_2024_3444602 crossref_primary_10_1109_TWC_2022_3192550 crossref_primary_10_1016_j_dsp_2023_104027 crossref_primary_10_1109_JIOT_2022_3173210 crossref_primary_10_1109_ACCESS_2020_3025597 crossref_primary_10_1109_COMST_2019_2924243 crossref_primary_10_3233_ICA_230722 crossref_primary_10_1109_JIOT_2021_3064150 crossref_primary_10_1109_LWC_2020_3007198 crossref_primary_10_1007_s11276_023_03635_8 crossref_primary_10_1109_JSAC_2024_3460084 crossref_primary_10_1109_LCOMM_2023_3246052 crossref_primary_10_1109_TVT_2021_3103521 crossref_primary_10_1109_TWC_2023_3249103 crossref_primary_10_1109_TCOMM_2022_3209888 crossref_primary_10_1109_TVT_2024_3371019 crossref_primary_10_1109_TWC_2022_3190435 crossref_primary_10_1109_TVT_2020_2972734 crossref_primary_10_1109_TVT_2020_2994525 crossref_primary_10_1109_TII_2023_3254651 crossref_primary_10_1109_TSP_2020_3000328 crossref_primary_10_3390_jsan10040060 crossref_primary_10_3390_app15010111 crossref_primary_10_1002_ett_3603 crossref_primary_10_1109_ACCESS_2021_3050522 crossref_primary_10_1109_TWC_2022_3204486 crossref_primary_10_1109_ACCESS_2021_3067070 crossref_primary_10_1109_JSTSP_2023_3239189 crossref_primary_10_1109_LCOMM_2021_3116233 crossref_primary_10_1109_TITS_2022_3165791 crossref_primary_10_3390_fi17060237 crossref_primary_10_1109_MNET_011_1900630 crossref_primary_10_1109_TIP_2023_3263109 crossref_primary_10_1109_TWC_2021_3111843 crossref_primary_10_3233_JIFS_179616 crossref_primary_10_1002_dac_6060 crossref_primary_10_1109_TWC_2025_3560619 crossref_primary_10_1109_MBITS_2022_3212978 crossref_primary_10_1109_ACCESS_2024_3381542 crossref_primary_10_1109_TCOMM_2019_2957482 crossref_primary_10_1109_TWC_2024_3483291 crossref_primary_10_1109_TWC_2023_3249165 crossref_primary_10_1186_s13638_025_02468_7 crossref_primary_10_1109_ACCESS_2020_3011026 crossref_primary_10_1109_TVT_2024_3381285 crossref_primary_10_1109_JIOT_2025_3547933 crossref_primary_10_1109_TCOMM_2019_2938514 crossref_primary_10_1109_ACCESS_2020_3004865 crossref_primary_10_1080_15325008_2023_2209081 crossref_primary_10_2478_jee_2024_0013 crossref_primary_10_1109_LWC_2021_3095500 crossref_primary_10_1109_TWC_2023_3243611 crossref_primary_10_12677_SEA_2023_123052 crossref_primary_10_1109_MNET_006_2200281 crossref_primary_10_1016_j_neucom_2025_129770 crossref_primary_10_1109_ACCESS_2019_2923321 crossref_primary_10_1049_cmu2_12605 crossref_primary_10_1109_TSP_2023_3244096 crossref_primary_10_3390_s23063034 crossref_primary_10_1109_TSP_2020_3030073 crossref_primary_10_1109_TNET_2021_3093452 crossref_primary_10_1109_TWC_2021_3100500 crossref_primary_10_1109_LCOMM_2020_3042490 crossref_primary_10_1109_ACCESS_2023_3321371 crossref_primary_10_3390_sym13091737 crossref_primary_10_1051_jnwpu_20234150887 crossref_primary_10_1109_TAES_2023_3285201 crossref_primary_10_1155_2020_8863865
Cites_doi	10.1137/080716542 10.1109/TSP.2006.872578 10.1109/TSP.2014.2331611 10.1109/SPAWC.2017.8227766 10.1109/26.975766 10.1109/TIT.2009.2023751 10.1109/MSP.2014.2335237 10.1016/0893-6080(89)90020-8 10.1109/TCOMM.2005.851626 10.1109/TSP.2011.2147784 10.1038/nature14539 10.1109/DySPAN.2017.7920754 10.1109/MSP.2010.936019 10.1109/MSRP.2009.933371 10.1109/JSTSP.2007.914876
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2018
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TSP.2018.2866382
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1941-0476
EndPage	5453
ExternalDocumentID	10_1109_TSP_2018_2866382 8444648
Genre	orig-research
GrantInformation_xml	– fundername: Fundamental Research Funds for the Central Universities funderid: 10.13039/501100012226 – fundername: National Science Foundation grantid: CMMI-1727757; CCF-1526078; CIF-1525194 funderid: 10.13039/501100008982 – fundername: National Natural Science Foundation of China; NSFC grantid: 61671411; U1709219; 61374020 funderid: 10.13039/501100001809 – fundername: Air Force Office of Scientific Research grantid: 15RT0767 funderid: 10.13039/100000181 – fundername: National Science Foundation grantid: CIF-1525194 funderid: 10.13039/501100008982 – fundername: Zhejiang Provincial NSF of China grantid: LR15F010002
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACIWK ACNCT AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RNS TAE TN5 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D RIG
ID	FETCH-LOGICAL-c333t-744f3292d06c946c9a01ad67a4cc3780adfe62ff2ef8d11582e171668debc25f3
IEDL.DBID	RIE
ISICitedReferencesCount	594
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000444842400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1053-587X
IngestDate	Mon Jun 30 10:16:43 EDT 2025 Sat Nov 29 04:10:47 EST 2025 Tue Nov 18 22:22:54 EST 2025 Wed Aug 27 08:34:58 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	20
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c333t-744f3292d06c946c9a01ad67a4cc3780adfe62ff2ef8d11582e171668debc25f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-6266-123X 0000-0003-4847-9586 0000-0002-3385-7911 0000-0003-0507-9080 0000-0003-1263-9365
OpenAccessLink	http://hdl.handle.net/20.500.11850/245053
PQID	2117167150
PQPubID	85478
PageCount	16
ParticipantIDs	proquest_journals_2117167150 crossref_citationtrail_10_1109_TSP_2018_2866382 ieee_primary_8444648 crossref_primary_10_1109_TSP_2018_2866382
PublicationCentury	2000
PublicationDate	2018-10-15
PublicationDateYYYYMMDD	2018-10-15
PublicationDate_xml	– month: 10 year: 2018 text: 2018-10-15 day: 15
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on signal processing
PublicationTitleAbbrev	TSP
PublicationYear	2018
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 verdu (ref25) 1998 samuel (ref20) 0 gregor (ref10) 2010 ref11 ref32 lee (ref29) 0 grzeszczuk (ref21) 1998 ref1 andrychowicz (ref14) 2016 ref18 farsad (ref17) 2017 hinton (ref30) 2012 glorot (ref31) 2010 ref24 karipidis (ref34) 2006; 2006 hong (ref33) 2013 bertsekas (ref26) 1997 ref27 o'shea (ref19) 2017 liang (ref28) 0 ref8 ref7 sprechmann (ref13) 0 ref9 li (ref15) 0 ref4 chen (ref22) 2017 ref3 sun (ref2) 0 ref6 ref5 luo (ref23) 2008; 2 hershey (ref12) 2014 o'shea (ref16) 2016
References_xml	– start-page: 9 year: 1998 ident: ref21 article-title: Neuroanimator: Fast neural network emulation and control of physics-based models publication-title: Proc 25th Annu Conf Comput Graph Interactive Tech – ident: ref11 doi: 10.1137/080716542 – year: 2014 ident: ref12 article-title: Deep unfolding: Model-based inspiration of novel deep architectures – year: 2016 ident: ref16 article-title: Recurrent neural radio anomaly detection – ident: ref8 doi: 10.1109/TSP.2006.872578 – ident: ref32 doi: 10.1109/TSP.2014.2331611 – ident: ref1 doi: 10.1109/SPAWC.2017.8227766 – volume: 2006 start-page: 90 year: 2006 ident: ref34 article-title: Crosstalk models for short VDSL2 lines from measured 30Mhz data publication-title: EURASIP J Appl Signal Process – year: 0 ident: ref15 article-title: Learning to optimize publication-title: Proc Int Conf Learn Represent – start-page: 46 year: 0 ident: ref2 article-title: Deep wireless interference management publication-title: Proc Int Zurich Seminar on Communication – ident: ref5 doi: 10.1109/26.975766 – ident: ref24 doi: 10.1109/TIT.2009.2023751 – year: 2012 ident: ref30 article-title: Lecture 6a overview of mini-batch gradient descent publication-title: Coursera Lecture slides – start-page: 908 year: 0 ident: ref13 article-title: Supervised sparse analysis and synthesis operators publication-title: Adv Neural Inf Process Syst – ident: ref4 doi: 10.1109/MSP.2014.2335237 – start-page: 249 year: 2010 ident: ref31 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref27 doi: 10.1016/0893-6080(89)90020-8 – year: 2017 ident: ref17 article-title: Detection algorithms for communication systems using deep learning – year: 1998 ident: ref25 publication-title: Multiuser Detection – ident: ref35 doi: 10.1109/TCOMM.2005.851626 – start-page: 1246 year: 0 ident: ref29 article-title: Gradient descent converges to minimizers publication-title: Proc Conf Learn Theory – year: 0 ident: ref28 article-title: Why deep neural networks for function approximation? publication-title: Proc Int Conf Learn Represent – ident: ref3 doi: 10.1109/TSP.2011.2147784 – ident: ref9 doi: 10.1038/nature14539 – start-page: 399 year: 2010 ident: ref10 article-title: Learning fast approximations of sparse coding publication-title: Proc 27th Int Conf Mach Learn – ident: ref18 doi: 10.1109/DySPAN.2017.7920754 – year: 2013 ident: ref33 article-title: Signal processing and optimal resource allocation for the interference channel publication-title: Academic Press Library in Signal Processing – year: 2017 ident: ref19 article-title: Deep learning based MIMO communications – ident: ref7 doi: 10.1109/MSP.2010.936019 – start-page: 2497 year: 2017 ident: ref22 article-title: Fast image processing with fully-convolutional networks publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref6 doi: 10.1109/MSRP.2009.933371 – start-page: 3981 year: 2016 ident: ref14 article-title: Learning to learn by gradient descent by gradient descent publication-title: Proc Adv Neural Inf Process Syst – year: 0 ident: ref20 article-title: Deep MIMO detection publication-title: proc IEEE 18th Int Workshop Signal Process Adv Wireless Commun – volume: 2 start-page: 57 year: 2008 ident: ref23 article-title: Dynamic spectrum management: Complexity and duality publication-title: IEEE J Sel Topics Signal Process doi: 10.1109/JSTSP.2007.914876 – year: 1997 ident: ref26 publication-title: Parallel and Distributed Computation Numerical Methods 2nd edition
SSID	ssj0014496
Score	2.7093766
Snippet	Numerical optimization has played a central role in addressing key signal processing (SP) problems. Highly effective methods have been developed for a large...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5438
SubjectTerms	Algorithms Approximation algorithms Artificial neural networks Computing time deep neural networks Design analysis Filter design (mathematics) Interference interference management Machine learning algorithms Management Mapping Neural networks Optimization Optimization algorithms Optimization algorithms approximation Radar imaging Signal processing Signal processing algorithms Task analysis Wireless communication WMMSE algorithm
Title	Learning to Optimize: Training Deep Neural Networks for Interference Management
URI	https://ieeexplore.ieee.org/document/8444648 https://www.proquest.com/docview/2117167150
Volume	66
WOSCitedRecordID	wos000444842400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE/IET Electronic Library customDbUrl: eissn: 1941-0476 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014496 issn: 1053-587X databaseCode: RIE dateStart: 19910101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwED6VigEGXgVRKMgDCxJpE9uJHTYEVExtJYrULUr8QJWgrdqUgV-P7bgFBEJiiJTBtpK7xHfnu_s-gIsilNqEsiyIBdUBlYIGaRHmQSJVzCMaCUG0I5tgvR4fjdJBDa7WvTBKKVd8ptr21uXy5VQs7VFZh1MTvFC-ARuMsapXa50xoNRxcRl3gQQxZ6NVSjJMO8PHga3h4m3MjX3l-JsJcpwqPzZiZ126u_97rj3Y8V4kuqnUvg81NTmA7S_Ygg3oe-TUZ1ROUd9sDK_jd3WNhp4SAt0pNUMWmsOs06tqwRfIeLDInRH6LkD0WR1zCE_d--HtQ-DZEwJBCCkDRqkmOMUyTERKzZWHUS4TllMjf8bDXGqVYK2x0lwav5BjZaFzEi5VIXCsyRHUJ9OJOgZE8rQQOU0LEtu8HymkMa00N-rFOJIFa0JnJdBMeGhxy3DxkrkQI0wzo4LMqiDzKmjC5XrGrILV-GNsw4p8Pc5Luwmtlc4y_98tMhPOmndgxss9-X3WKWzZta31ieIW1Mv5Up3Bpngrx4v5ufukPgA1ycnC
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5qFdSDb7FadQ9eBNMmu5tk403UUrG2BSv0FpJ9SEHb0ocHf727221VFMFDIIfdPOZLdmZ2Zr4BOMt9obQrG3shp8qjglMvyf3Mi4QMWUADzomyzSbiZpN1u0m7ABeLWhgppU0-kxVzamP5YsCnZqusyqh2XihbguWQUhzMqrUWMQNKbTcubTAQL2Rxdx6U9JNq57FtsrhYBTOtYRn-poRsV5UfS7HVL7XN_z3ZFmw4OxJdzYDfhoLs78D6F3bBXWg57tRnNBmgll4aXnvv8hJ1XFMIdCPlEBlyDn2d5iwbfIy0DYvsLqGrA0Sf-TF78FS77VzXPdc_weOEkIkXU6oITrDwI55QfWR-kIkozqhGIGZ-JpSMsFJYKia0ZciwNOQ5ERMy5zhUZB-K_UFfHgAiWZLzjCY5CU3kj-RCK1eaaYAxDkQel6A6F2jKHbm46XHxklonw09SDUFqIEgdBCU4X8wYzog1_hi7a0S-GOekXYLyHLPU_XnjVDu0-h1ibece_j7rFFbrnYdG2rhr3h_BmrmP0UVBWIbiZDSVx7DC3ya98ejEfl4f3n7NCQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+to+Optimize%3A+Training+Deep+Neural+Networks+for+Interference+Management&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Sun%2C+Haoran&rft.au=Chen%2C+Xiangyi&rft.au=Shi%2C+Qingjiang&rft.au=Hong%2C+Mingyi&rft.date=2018-10-15&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=66&rft.issue=20&rft.spage=5438&rft_id=info:doi/10.1109%2FTSP.2018.2866382&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon