{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:29:15Z","timestamp":1781368155412,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413662","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"3890-3894","source":"Crossref","is-referenced-by-count":2,"title":["Convex Neural Autoregressive Models: Towards Tractable, Expressive, and Theoretically-Backed Models for Sequential Forecasting and Generation"],"prefix":"10.1109","author":[{"given":"Vikul","family":"Gupta","sequence":"first","affiliation":[{"name":"Stanford University,Department of Electrical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Burak","family":"Bartan","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Electrical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tolga","family":"Ergen","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Electrical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mert","family":"Pilanci","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Electrical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","article-title":"M-ihs: An accelerated randomized preconditioning method avoiding costly matrix decompositions","author":"ozaslan","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682720"},{"key":"ref30","article-title":"Effective dimension adaptive sketching methods for faster regularized least-squares optimization","author":"lacotte","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","article-title":"Provable bounds for learning some deep representations","author":"arora","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Beating the perils of non-convexity: Guaranteed training of neural networks using tensor methods","author":"janzamin","year":"0"},{"key":"ref12","article-title":"Provable methods for training neural networks with sparse connectivity","author":"sedghi","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref13","article-title":"Brutzkus and amir globerson. globally optimal gradient descent for a convnet with gaussian inputs","year":"0"},{"key":"ref14","article-title":"Learning one-hidden-layer neural networks with landscape design","author":"ge","year":"0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref16","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","author":"jacot","year":"0","journal-title":"Neural Information Processing Systems"},{"key":"ref17","article-title":"Implicit convex regularizers of cnn architectures: Convex optimization of two-and three-layer networks in polynomial time","author":"ergen","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref18","article-title":"Vector-output relu neural network problems are copositive programs: Convex analysis of two layer networks and polynomial-time algorithms","author":"sahiner","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","article-title":"Convex regularization behind neural reconstruction","author":"sahiner","year":"2021","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref28","article-title":"Optimal iterative sketching with the subsampled randomized hadamard transform","author":"lacotte","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Neural autoregressive distribution estimation","author":"uria","year":"0","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","first-page":"5587","article-title":"Optimal randomized first-order methods for least-squares problems","author":"lacotte","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Deep autoregressive networks","author":"gregor","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref6","article-title":"Generative pretraining from pixels","author":"chen","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref29","article-title":"Faster least squares optimization","author":"lacotte","year":"2019"},{"key":"ref5","article-title":"pixel recurrent neural networks","author":"van den oord","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref7","article-title":"Nal kalchbrenner, andrew senior, and koray kavukcuoglu","author":"oord","year":"0","journal-title":"WaveNet A Generative Model for Raw Audio"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3261-0","author":"shumway","year":"0","journal-title":"Time Series Analysis and its Applications"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390266"},{"key":"ref20","article-title":"Neural spectrahedra and semidefinite lifts: Global convex optimization of polynomial activation neural networks in fully polynomial-time","author":"bartan","year":"2021"},{"key":"ref22","first-page":"7695","article-title":"Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks","author":"pilanci","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref21","article-title":"All local minima are global for two-layer relu neural networks: The hidden convex optimization landscape","author":"lacotte","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2007.00627.x"},{"key":"ref26","article-title":"Adaptive and oblivious randomized subspace methods for high-dimensional optimization: Sharp analysis and lower bounds","author":"lacotte","year":"2020"},{"key":"ref25","first-page":"10847","article-title":"High-dimensional optimization in adaptive random subspaces","author":"lacotte","year":"2019","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413662.pdf?arnumber=9413662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:19:35Z","timestamp":1659471575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413662","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}