{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T12:07:58Z","timestamp":1762430878517,"version":"3.41.0"},"reference-count":33,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2014,5,2]],"date-time":"2014-05-02T00:00:00Z","timestamp":1398988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Model. Comput. Simul."],"published-print":{"date-parts":[[2014,5,2]]},"abstract":"<jats:p>\n            Smoothed functional (SF) schemes for gradient estimation are known to be efficient in stochastic optimization algorithms, especially when the objective is to improve the performance of a stochastic system. However, the performance of these methods depends on several parameters, such as the choice of a suitable smoothing kernel. Different kernels have been studied in the literature, which include Gaussian, Cauchy, and uniform distributions, among others. This article studies a new class of kernels based on the\n            <jats:italic>q<\/jats:italic>\n            -Gaussian distribution, which has gained popularity in statistical physics over the last decade. Though the importance of this family of distributions is attributed to its ability to generalize the Gaussian distribution, we observe that this class encompasses almost all existing smoothing kernels. This motivates us to study SF schemes for gradient estimation using the\n            <jats:italic>q<\/jats:italic>\n            -Gaussian distribution. Using the derived gradient estimates, we propose two-timescale algorithms for optimization of a stochastic objective function in a constrained setting with a projected gradient search approach. We prove the convergence of our algorithms to the set of stationary points of an associated ODE. We also demonstrate their performance numerically through simulations on a queuing model.\n          <\/jats:p>","DOI":"10.1145\/2628434","type":"journal-article","created":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T14:23:02Z","timestamp":1404224582000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Smoothed Functional Algorithms for Stochastic Optimization Using\n            <i>q<\/i>\n            -Gaussian Distributions"],"prefix":"10.1145","volume":"24","author":[{"given":"Debarghya","family":"Ghoshdastidar","sequence":"first","affiliation":[{"name":"Indian Institute of Science, Bangalore, India"}]},{"given":"Ambedkar","family":"Dukkipati","sequence":"additional","affiliation":[{"name":"Indian Institute of Science, Bangalore, India"}]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science, Bangalore, India"}]}],"member":"320","published-online":{"date-parts":[[2014,6]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1315575.1315577"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269964800005362"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/0037549703039988"},{"volume-title":"Stochastic approximation: A dynamical systems viewpoint","author":"Borkar V. S.","key":"e_1_2_1_4_1","unstructured":"V. S. Borkar . 2008. Stochastic approximation: A dynamical systems viewpoint . Cambridge University Press . V. S. Borkar. 2008. Stochastic approximation: A dynamical systems viewpoint. Cambridge University Press."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299630759X"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0927-0507(06)13019-4"},{"volume-title":"IEEE Int. Symp. Inf. Theory (ISIT).","author":"Ghoshdastidar D.","key":"e_1_2_1_7_1","unstructured":"D. Ghoshdastidar , A. Dukkipati , and S. Bhatnagar . 2012. q-Gaussian based smoothed functional algorithms for stochastic optimization . In IEEE Int. Symp. Inf. Theory (ISIT). D. Ghoshdastidar, A. Dukkipati, and S. Bhatnagar. 2012. q-Gaussian based smoothed functional algorithms for stochastic optimization. In IEEE Int. Symp. Inf. Theory (ISIT)."},{"key":"e_1_2_1_8_1","unstructured":"I. S. Gradshteyn and I. M. Ryzhik. 1994. Table of Integrals Series and Products (5th ed.). Elsevier.  I. S. Gradshteyn and I. M. Ryzhik. 1994. Table of Integrals Series and Products (5th ed.). Elsevier."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90018-X"},{"key":"e_1_2_1_10_1","first-page":"1321","article-title":"Convergence of a class of random search algorithms. Auto","volume":"8","author":"Katkovnik V. Y. A.","year":"1972","unstructured":"V. Y. A. Katkovnik and Y. U. Kulchitsky . 1972 . Convergence of a class of random search algorithms. Auto . Remote Control 8 (1972), 1321 -- 1326 . V. Y. A. Katkovnik and Y. U. Kulchitsky. 1972. Convergence of a class of random search algorithms. Auto. Remote Control 8 (1972), 1321--1326.","journal-title":"Remote Control"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1137\/0725031"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02060937"},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"H. J. Kushner and D. S. Clark. 1978. Stochastic approximation methods for constrained and unconstrained systems. Springer-Verlag New York.  H. J. Kushner and D. S. Clark. 1978. Stochastic approximation methods for constrained and unconstrained systems. Springer-Verlag New York.","DOI":"10.1007\/978-1-4684-9352-8"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.40.11.1562"},{"key":"e_1_2_1_16_1","first-page":"2398","article-title":"Nonextensive foundation of L\u00e9vy distributions. Phy","volume":"60","author":"Prato D.","year":"1999","unstructured":"D. Prato and C. Tsallis . 1999 . Nonextensive foundation of L\u00e9vy distributions. Phy . Rev. E. 60 (1999), 2398 . D. Prato and C. Tsallis. 1999. Nonextensive foundation of L\u00e9vy distributions. Phy. Rev. E. 60 (1999), 2398.","journal-title":"Rev. E."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"volume-title":"Simulation and Monte-Carlo method","author":"Rubinstein R. Y.","key":"e_1_2_1_18_1","unstructured":"R. Y. Rubinstein . 1981. Simulation and Monte-Carlo method . John Wiley , New York . R. Y. Rubinstein. 1981. Simulation and Monte-Carlo method. John Wiley, New York."},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346589"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/201\/1\/012008"},{"key":"e_1_2_1_21_1","doi-asserted-by":"crossref","unstructured":"P. J. Schweitzer. 1968. Perturbation theory and finite Markov chains. J. Appl. Prob. (1968) 401--413.  P. J. Schweitzer. 1968. Perturbation theory and finite Markov chains. J. Appl. Prob. (1968) 401--413.","DOI":"10.1017\/S0021900200110083"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2000.880982"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90029-K"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/28869.28879"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.840862"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.909173"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01016429"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4371(98)00437-3"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.2307\/3214571"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2006.01.028"},{"key":"e_1_2_1_32_1","article-title":"Central limit theorem and deformed exponentials","volume":"20","author":"Vignat C.","year":"2007","unstructured":"C. Vignat and A. Plastino . 2007 . Central limit theorem and deformed exponentials . J. Phy. A 20 , 45 (2007). C. Vignat and A. Plastino. 2007. Central limit theorem and deformed exponentials. J. Phy. A 20, 45 (2007).","journal-title":"J. Phy. A"},{"volume-title":"Probability with Martingales","author":"Williams D.","key":"e_1_2_1_33_1","unstructured":"D. Williams . 1991. Probability with Martingales . Cambridge University Press . D. Williams. 1991. Probability with Martingales. Cambridge University Press."}],"container-title":["ACM Transactions on Modeling and Computer Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2628434","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2628434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:19:29Z","timestamp":1750231169000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2628434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,2]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,5,2]]}},"alternative-id":["10.1145\/2628434"],"URL":"https:\/\/doi.org\/10.1145\/2628434","relation":{},"ISSN":["1049-3301","1558-1195"],"issn-type":[{"type":"print","value":"1049-3301"},{"type":"electronic","value":"1558-1195"}],"subject":[],"published":{"date-parts":[[2014,5,2]]},"assertion":[{"value":"2013-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2014-05-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2014-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}