{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/amc-automl-for-model-compression-and","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","arxiv_id":"1802.03494","date":"2018-02-10","proceeding":"ECCV 2018 9","authors":["Yihui He","Ji Lin","Zhijian Liu","Hanrui Wang","Li-Jia Li","Song Han"],"abstract":"Model compression is a critical technique to efficiently deploy neural\nnetwork models on mobile devices which have limited computation resources and\ntight power budgets. Conventional model compression techniques rely on\nhand-crafted heuristics and rule-based policies that require domain experts to\nexplore the large design space trading off among model size, speed, and\naccuracy, which is usually sub-optimal and time-consuming. In this paper, we\npropose AutoML for Model Compression (AMC) which leverage reinforcement\nlearning to provide the model compression policy. This learning-based\ncompression policy outperforms conventional rule-based compression policy by\nhaving higher compression ratio, better preserving the accuracy and freeing\nhuman labor. Under 4x FLOPs reduction, we achieved 2.7% better accuracy than\nthe handcrafted model compression policy for VGG-16 on ImageNet. We applied\nthis automated, push-the-button compression pipeline to MobileNet and achieved\n1.81x speedup of measured inference latency on an Android phone and 1.43x\nspeedup on the Titan XP GPU, with only 0.1% loss of ImageNet Top-1 accuracy.","url_abs":"http://arxiv.org/abs/1802.03494v4","url_pdf":"http://arxiv.org/pdf/1802.03494v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/mit-han-lab/amc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/AhmadQasim/proxylessnas-dense","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/ZTao-z/ProxylessNAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/ito-rafael/once-for-all-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/mit-han-lab/ProxylessNAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/mit-han-lab/haq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/mit-han-lab/haq-release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/mit-han-lab/once-for-all","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/seulkiyeom/once-for-all","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/songhan/DSD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/songhan/SqueezeNet-Residual","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"amc-automl-for-model-compression-and","repo_url":"https://github.com/NervanaSystems/distiller","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"tasks":[{"task_slug":"automl","task_name":"AutoML"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.03494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.03494"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/ProxylessNAS","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/haq-release","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZTao-z/ProxylessNAS","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/once-for-all","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/haq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mit-han-lab/amc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ito-rafael/once-for-all-2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seulkiyeom/once-for-all","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AhmadQasim/proxylessnas-dense","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NervanaSystems/distiller","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/songhan/SqueezeNet-Residual","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/songhan/DSD","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"53fba30b1d44a663","entry":"adjust_learning_rate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"53fba30b1d44a663"}},{"code_sha256_prefix":"2055ca9836e34f1a","entry":"get_model_and_checkpoint","repo":"mit-han-lab/amc","repo_kind":"official","path":"amc_search.py","file_url":"https://github.com/mit-han-lab/amc/blob/HEAD/amc_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2055ca9836e34f1a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}