{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T05:40:56Z","timestamp":1732686056637,"version":"3.28.2"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,22]],"date-time":"2024-09-22T00:00:00Z","timestamp":1726963200000},"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":[[2024,9,22]]},"DOI":"10.1109\/mlsp58920.2024.10734837","type":"proceedings-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:31:55Z","timestamp":1730745115000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["ConQ: Binary Quantization of Neural Networks via Concave Regularization"],"prefix":"10.1109","author":[{"given":"Andrea","family":"Migliorati","sequence":"first","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Turin,Italy"}]},{"given":"Giulia","family":"Fracastoro","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Turin,Italy"}]},{"given":"Sophie","family":"Fosson","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Control and Computer Engineering,Turin,Italy"}]},{"given":"Tiziano","family":"Bianchi","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Turin,Italy"}]},{"given":"Enrico","family":"Magli","sequence":"additional","affiliation":[{"name":"Politecnico di Torino,Department of Electronics and Telecommunications,Turin,Italy"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","volume":"28","author":"Courbariaux","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","article-title":"Proxquant: Quantized neural networks via proximal operators","volume-title":"International Conf. on Learning Representations","author":"Bai","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"ref4","first-page":"3644","article-title":"Askewsgd: an annealed interval-constrained optimisation method to train quantized neural networks","volume-title":"Int. Conf. on Artificial Intelligence and Statistics","author":"Leconte","year":"2023"},{"key":"ref5","article-title":"ProxSGD: Training structured neural networks under regularization and constraints","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yang","year":"2020"},{"key":"ref6","first-page":"24365","article-title":"Adaptive proximal gradient methods for structured neural networks","volume":"34","author":"Yun","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","first-page":"13202","article-title":"Demystifying and generalizing BinaryConnect","volume":"34","author":"Dockhorn","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107281"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10464-w"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-70139-4","article-title":"Training quantized nets: A deeper understanding","volume":"30","author":"Li","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"The high-dimensional geometry of binary neural networks","volume-title":"International Conference on Learning Representations","author":"Anderson","year":"2018"},{"key":"ref12","article-title":"BiBench: Benchmarking and analyzing network binarization","volume-title":"Proceedings of Int. Conf. on Machine Learning","author":"Qin","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/18M1166134"},{"key":"ref14","article-title":"Loss-aware binarization of deep networks","volume-title":"International Conf. on Learning Representations","author":"Hou","year":"2017"},{"key":"ref15","article-title":"Loss-aware weight quantization of deep networks","volume-title":"International Conf. on Learning Representations","author":"Hou","year":"2018"},{"key":"ref16","article-title":"Model compression as constrained optimization, with application to neural nets. part i: General framework","author":"Carreira-Perpin\u00e1n","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Understanding neural network binarization with forward and backward proximal quantizers","author":"Lu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0449"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-011-0484-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-09-05048-X"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5802\/aif.1638"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-014-0642-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref25","first-page":"6","article-title":"A method for stochastic optimization","volume-title":"Int. conf. on Learning Representations","volume":"5","author":"Kingma","year":"2015"},{"key":"ref26","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke","year":"2019"},{"key":"ref27","article-title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients","author":"Zhou","year":"2016","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00232"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref31","first-page":"6852","article-title":"Training binary neural networks using the bayesian learning rule","volume-title":"International conference on machine learning","author":"Meng","year":"2020"},{"key":"ref32","first-page":"2809","article-title":"Mirror descent view for neural network quantization","volume-title":"International conference on artificial intelligence and statistics","author":"Ajanthan","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00497"}],"event":{"name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2024,9,22]]},"location":"London, United Kingdom","end":{"date-parts":[[2024,9,25]]}},"container-title":["2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10734669\/10734712\/10734837.pdf?arnumber=10734837","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T03:59:52Z","timestamp":1732679992000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734837\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/mlsp58920.2024.10734837","relation":{},"subject":[],"published":{"date-parts":[[2024,9,22]]}}}