{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:10:08Z","timestamp":1743124208055,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819784899"},{"type":"electronic","value":"9789819784905"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8490-5_27","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T09:09:07Z","timestamp":1730884147000},"page":"376-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reducing Memory Footprint in Deep Network Training by Gradient Space Reutilization"],"prefix":"10.1007","author":[{"given":"Yiming","family":"Dong","sequence":"first","affiliation":[]},{"given":"Zhouchen","family":"Lin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"27_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR2","unstructured":"Almazrouei, E., Alobeidli, H., Alshamsi, A., Cappelli, A., Cojocaru, R., et\u00a0al.: The Falcon series of open language models. arXiv preprint arXiv:2311.16867 (2023)"},{"key":"27_CR3","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., Dang, K., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"27_CR4","unstructured":"Bojarski, M., Del\u00a0Testa, D., Dworakowski, D., Firner, B., Flepp, B., et\u00a0al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"27_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR6","unstructured":"Chen, T., Xu, B., Zhang, C., Guestrin, C.: Training deep nets with sublinear memory cost. arXiv preprint arXiv:1604.06174 (2016)"},{"key":"27_CR7","unstructured":"Chen, X., Liang, C., Huang, D., Real, E., Wang, K., et\u00a0al.: Symbolic discovery of optimization algorithms. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"27_CR8","unstructured":"Chiang, W.L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J.E., Stoica, I., Xing, E.P.: Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (March 2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"issue":"1","key":"27_CR9","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s41524-022-00734-6","volume":"8","author":"K Choudhary","year":"2022","unstructured":"Choudhary, K., DeCost, B., Chen, C., Jain, A., Tavazza, F., et al.: Recent advances and applications of deep learning methods in materials science. NPJ Comput. Mater. 8(1), 59 (2022)","journal-title":"NPJ Comput. Mater."},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"27_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"27_CR12","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR13","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(7) (2011)"},{"key":"27_CR14","unstructured":"Gruslys, A., Munos, R., Danihelka, I., Lanctot, M., Graves, A.: Memory-efficient backpropagation through time. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"27_CR15","unstructured":"Gunasekar, S., Zhang, Y., Aneja, J., Mendes, C.C.T., Del\u00a0Giorno, A., et\u00a0al.: Textbooks are all you need. arXiv preprint arXiv:2306.11644 (2023)"},{"key":"27_CR16","first-page":"5290","volume":"34","author":"L He","year":"2021","unstructured":"He, L., Chen, Y., Dong, Y., Wang, Y., Lin, Z., et al.: Efficient equivariant network. Adv. Neural. Inf. Process. Syst. 34, 5290\u20135302 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR17","first-page":"27331","volume":"34","author":"L He","year":"2021","unstructured":"He, L., Dong, Y., Wang, Y., Tao, D., Lin, Z.: Gauge equivariant transformer. Adv. Neural. Inf. Process. Syst. 34, 27331\u201327343 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR18","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"27_CR19","first-page":"497","volume":"2","author":"P Jain","year":"2020","unstructured":"Jain, P., Jain, A., Nrusimha, A., Gholami, A., Abbeel, P., Gonzalez, J., Keutzer, K., Stoica, I.: Checkmate: Breaking the memory wall with optimal tensor rematerialization. Proc. Mach. Learn. Syst. 2, 497\u2013511 (2020)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"27_CR20","unstructured":"Kaddour, J., Harris, J., Mozes, M., Bradley, H., Raileanu, R., McHardy, R.: Challenges and applications of large language models. arXiv preprint arXiv:2307.10169 (2023)"},{"key":"27_CR21","unstructured":"Kalamkar, D., Mudigere, D., Mellempudi, N., Das, D., Banerjee, K., et\u00a0al.: A study of BFLOAT16 for deep learning training. arXiv preprint arXiv:1905.12322 (2019)"},{"key":"27_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"27_CR23","unstructured":"Le\u00a0Scao, T., Fan, A., Akiki, C., Pavlick, E., Ili\u0107, S., et\u00a0al.: BLOOM: A 176B-parameter open-access multilingual language model (2022)"},{"issue":"7553","key":"27_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"27_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"27_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"27_CR27","unstructured":"Mehta, S., Shah, D., Kulkarni, R., Caragea, C.: Semantic tokenizer for enhanced natural language processing. arXiv preprint arXiv:2304.12404 (2023)"},{"key":"27_CR28","unstructured":"Micikevicius, P., Narang, S., Alben, J., Diamos, G., Elsen, E., et\u00a0al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"issue":"3","key":"27_CR29","first-page":"543","volume":"269","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method of solving a convex programming problem with convergence rate O(1\/k2). Dokl. Akad. Nauk SSSR 269(3), 543 (1983)","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"27_CR30","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., Lerer, A.: Automatic differentiation in PyTorch. In: NIPS 2017 Workshop on Autodiff (2017)"},{"key":"27_CR31","unstructured":"Pleiss, G., Chen, D., Huang, G., Li, T., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Memory-efficient implementation of DenseNets. arXiv preprint arXiv:1707.06990 (2017)"},{"issue":"8","key":"27_CR32","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"27_CR33","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: ZeRO: Memory optimizations toward training trillion parameter models. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316 (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"27_CR34","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: DeepSpeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"issue":"1","key":"27_CR35","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR36","unstructured":"Taori, R., Gulrajani, I., Zhang, T., Dubois, Y., Li, X., Guestrin, C., Liang, P., Hashimoto, T.B.: Stanford Alpaca: An instruction-Following LLaMA Model (2023)"},{"key":"27_CR37","unstructured":"Team, G., Mesnard, T., Hardin, C., Dadashi, R., Bhupatiraju, S., et\u00a0al.: Gemma: Open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"27_CR38","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., et\u00a0al.: LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"issue":"2","key":"27_CR39","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s41573-023-00832-0","volume":"23","author":"A Tropsha","year":"2024","unstructured":"Tropsha, A., Isayev, O., Varnek, A., Schneider, G., Cherkasov, A.: Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR. Nat. Rev. Drug Discovery 23(2), 141\u2013155 (2024)","journal-title":"Nat. Rev. Drug Discovery"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Wang, L., Ye, J., Zhao, Y., Wu, W., Li, A., Song, S.L., Xu, Z., Kraska, T.: Superneurons: Dynamic GPU memory management for training deep neural networks. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 41\u201353 (2018)","DOI":"10.1145\/3178487.3178491"},{"key":"27_CR41","unstructured":"Wang, N., Choi, J., Brand, D., Chen, C.Y., Gopalakrishnan, K.: Training deep neural networks with 8-bit floating point numbers. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"27_CR42","unstructured":"Xie, X., Zhou, P., Li, H., Lin, Z., Yan, S.: Adan: Adaptive nesterov momentum algorithm for faster optimizing deep models. arXiv preprint arXiv:2208.06677 (2022)"},{"key":"27_CR43","unstructured":"Zeng, A., Liu, X., Du, Z., Wang, Z., Lai, H., et\u00a0al.: GLM-130B: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8490-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T09:16:28Z","timestamp":1730884588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8490-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819784899","9789819784905"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8490-5_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}