{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T04:02:00Z","timestamp":1788580920400,"version":"build-2803163510"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06867-3","type":"journal-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:03:44Z","timestamp":1735376624000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Vision transformer-based meta loss landscape exploration with actor-critic method"],"prefix":"10.1007","volume":"81","author":[{"given":"Enzhi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingbang","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaharu","family":"Munetomo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"6867_CR1","unstructured":"Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. In: arXiv preprint arXiv:1608.03983"},{"key":"6867_CR2","unstructured":"Keskar NS, et al (2016) On large-batch training for deep learning: generalization gap and sharp minima. In: arXiv preprint arXiv:1609.04836"},{"key":"6867_CR3","doi-asserted-by":"crossref","unstructured":"Deng J, (2009) Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE. pp. 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"6867_CR4","first-page":"929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. Jo Mach Learn Res 15(1):929\u20131958","journal-title":"Jo Mach Learn Res"},{"key":"6867_CR5","unstructured":"Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. In: arXiv preprint arXiv:1412.6572"},{"key":"6867_CR6","unstructured":"Madry A, et al (2017) Towards deep learning models resistant to adversarial attacks. In: arXiv preprint arXiv:1706.06083"},{"issue":"1","key":"6867_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J. Big Data 6(1):1\u201348","journal-title":"J. Big Data"},{"key":"6867_CR8","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. In: arXiv preprint arXiv:1412.6980"},{"key":"6867_CR9","unstructured":"Vanschoren J (2018) Meta-learning: a survey. In: arXiv preprint arXiv:1810.03548"},{"key":"6867_CR10","unstructured":"Franceschi L, et al (2018) Bilevel programming for hyperparameter optimization and meta-learning. In: International Conference on Machine Learning. PMLR. pp.\u00a01568\u20131577"},{"key":"6867_CR11","unstructured":"Jomaa HS, Grabocka J, Schmidt-Thieme L (2019) Hyp-rl: hyperparameter optimization by reinforcement learning. In: arXiv preprint arXiv:1906.11527"},{"key":"6867_CR12","unstructured":"Lorraine J, Vicol P, Duvenaud D (2020) Optimizing millions of hyperparameters by implicit differentiation. In: International Conference on Artificial Intelligence and Statistics. PMLR. pp.\u00a01540\u20131552"},{"key":"6867_CR13","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning. PMLR. pp.\u00a01126\u20131135"},{"key":"6867_CR14","unstructured":"Li K, Malik J (2016) Learning to optimize. In: arXiv preprint arXiv:1606.01885"},{"key":"6867_CR15","doi-asserted-by":"publisher","unstructured":"Zhang E, Wahib M, Munetomo M (2022) Learning from the past: regularization by validation. In: 2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS &ISIS). , pp.\u00a01\u20138. https:\/\/doi.org\/10.1109\/SCISISIS55246.2022.10002143","DOI":"10.1109\/SCISISIS55246.2022.10002143"},{"issue":"7540","key":"6867_CR16","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"6867_CR17","unstructured":"Konda V, Tsitsiklis J (1999) Actor-critic algorithms. In: Advances in Neural Information Processing Systems. 12"},{"key":"6867_CR18","unstructured":"Haarnoja T et al (2018) Soft actor-critic algorithms and applications. In: arXiv preprint arXiv:1812.05905"},{"key":"6867_CR19","unstructured":"Li H, et al (2018) Visualizing the loss landscape of neural nets. In: Advances in Neural Information Processing Systems. 31"},{"key":"6867_CR20","unstructured":"Garipov T, et al (2018) Loss surfaces, mode connectivity, and fast ensembling of dnns. In: Advances in Neural Information Processing Systems. 31"},{"key":"6867_CR21","unstructured":"Izmailov P et al (2018) Averaging weights leads to wider optima and better generalization. In: arXiv preprint arXiv:1803.05407"},{"key":"6867_CR22","unstructured":"Foret P, et al (2020) Sharpness-aware minimization for efficiently improving generalization. In: arXiv preprint arXiv:2010.01412"},{"key":"6867_CR23","unstructured":"Li Z, et al (2017) Meta-sgd: Learning to learn quickly for few-shot learning. In: arXiv preprint arXiv:1707.09835"},{"key":"6867_CR24","unstructured":"Antoniou A, Edwards H, Storkey, A (2018) How to train your MAML. In: arXiv preprint arXiv:1810.09502"},{"key":"6867_CR25","unstructured":"You Y, Gitman I, Ginsburg B (2017) Scaling sgd batch size to 32k for imagenet training. In: arXiv preprint arXiv:1708.03888 6(12) , p.\u00a06"},{"key":"6867_CR26","unstructured":"Pham H, et al (2018) Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning. PMLR. pp. 4095\u20134104"},{"key":"6867_CR27","unstructured":"Li Y, et al (2020) Neural architecture search in a proxy validation loss landscape. pp.\u00a05853\u20135862"},{"key":"6867_CR28","unstructured":"Alexey D, et al (2020) An image is worth 16x16 words: Transformers for image recognition at scale. In: arXiv preprint arXiv:2010.11929"},{"key":"6867_CR29","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press"},{"issue":"6","key":"6867_CR30","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng L (2012) The mnist database of handwritten digit images for machine learning research. IEEE Signal Process. Mag. 29(6):141\u2013142","journal-title":"IEEE Signal Process. Mag."},{"key":"6867_CR31","unstructured":"Alex K, Vinod N, Geoffrey H CIFAR-10 (Canadian Institute for Advanced Research). http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"6867_CR32","unstructured":"Alex K, Vinod N, Geoffrey H CIFAR-100 (Canadian Institute for Advanced Research). http:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"6867_CR33","doi-asserted-by":"publisher","unstructured":"Kim YJ et al (2021) PAIP 2019: Liver cancer segmentation challenge. In: Medical Image Analysis 67, p.\u00a0101854. ISSN: 1361-8415. https:\/\/doi.org\/10.1016\/j.media.2020.101854. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1361841520302188","DOI":"10.1016\/j.media.2020.101854"},{"key":"6867_CR34","doi-asserted-by":"crossref","unstructured":"He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp.\u00a0770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6867_CR35","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings. pp.\u00a0249\u2013256"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06867-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06867-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06867-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T10:03:03Z","timestamp":1735380183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06867-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6867"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06867-3","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"19 December 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"350"}}