{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:52:53Z","timestamp":1782406373159,"version":"3.54.5"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651182","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["Validation Loss Landscape Exploration with Deep Q-Learning"],"prefix":"10.1109","author":[{"given":"Enzhi","family":"Zhang","sequence":"first","affiliation":[{"name":"Hokkaido University,Grad. School of Info. Science and Technology,Sapporo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hokkaido University,Grad. School of Info. Science and Technology,Sapporo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaharu","family":"Munetomo","sequence":"additional","affiliation":[{"name":"Hokkaido University,Information Initiative Center,Sapporo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Wahib","sequence":"additional","affiliation":[{"name":"RIKEN Center for Computational Science,Kobe,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref2","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"Keskar","year":"2016"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"1","key":"ref4","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"key":"ref5","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014"},{"key":"ref6","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref8","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref9","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017"},{"key":"ref10","article-title":"Meta-learning: A survey","author":"Vanschoren","year":"2018"},{"key":"ref11","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"International Conference on Machine Learning","author":"Franceschi"},{"key":"ref12","article-title":"Hyp-rl: Hyperparameter optimization by reinforcement learning","author":"Jomaa","year":"2019"},{"key":"ref13","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Lorraine"},{"key":"ref14","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"International conference on machine learning","author":"Finn"},{"key":"ref15","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"2018"},{"key":"ref16","article-title":"Learning to optimize","author":"Li","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","volume":"31","author":"Garipov","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Averaging weights leads to wider optima and better generalization","author":"Izmailov","year":"2018"},{"key":"ref21","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"Foret","year":"2020"},{"key":"ref22","article-title":"Meta-sgd: Learning to learn quickly for few-shot learning","author":"Li","year":"2017"},{"key":"ref23","article-title":"How to train your maml","author":"Antoniou","year":"2018"},{"issue":"12","key":"ref24","first-page":"6","article-title":"Scaling sgd batch size to 32k for imagenet training","volume":"6","author":"You","year":"2017"},{"key":"ref25","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","volume-title":"International conference on machine learning","author":"Pham"},{"key":"ref26","first-page":"5853","article-title":"Neural architecture search in a proxy validation loss landscape","author":"Li","year":"2020"},{"key":"ref27","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref28","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","volume":"2","author":"Morgan","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Comparing biases for minimal network construction with back-propagation","volume":"1","author":"Hanson","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref31","article-title":"Cifar-10 (canadian institute for advanced research)","author":"Krizhevsky"},{"key":"ref32","article-title":"Cifar-100 (canadian institute for advanced research)","author":"Krizhevsky"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings","author":"Glorot"},{"key":"ref35","article-title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","author":"Goyal","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref37","article-title":"Practical bayesian optimization of machine learning algorithms","volume":"25","author":"Snoek","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref38","first-page":"1165","article-title":"Forward and reverse gradient-based hyperparameter optimization","volume-title":"International Conference on Machine Learning","author":"Franceschi"},{"key":"ref39","article-title":"Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions","author":"MacKay","year":"2019"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651182.pdf?arnumber=10651182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:36:14Z","timestamp":1725942974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651182","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}