{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/gradient-checkpointing","slug":"gradient-checkpointing","name":"Gradient Checkpointing","full_name":"Gradient Checkpointing","full_name_withheld":false,"description_markdown":"**Gradient Checkpointing** is a method used for reducing the memory footprint when training deep neural networks, at the cost of having a small increase in computation time.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Training Deep Nets with Sublinear Memory Cost","paper":"/paper/training-deep-nets-with-sublinear-memory-cost","first_author":"Tianqi Chen","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/training-deep-nets-with-sublinear-memory-cost"},"source":{"url":"http://arxiv.org/abs/1604.06174v2","title":"Training Deep Nets with Sublinear Memory Cost","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Stochastic Optimization","url":"/methods/category/stochastic-optimization","pwc_aliases":[]}],"n_papers_tagged":14,"archive_num_papers":14,"papers_newest_first":[{"paper":null,"slug":"optimal-gradient-checkpointing-for-sparse-and","title":"Optimal Gradient Checkpointing for Sparse and Recurrent Architectures using Off-Chip Memory","date":"2024-12-16","arxiv_id":"2412.11810","n_code_links":0,"syntology":null},{"paper":null,"slug":"look-every-frame-all-at-once-video-ma-2-mba","title":"Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing","date":"2024-11-29","arxiv_id":"2411.19460","n_code_links":0,"syntology":null},{"paper":"/paper/superior-scoring-rules-for-probabilistic","slug":"superior-scoring-rules-for-probabilistic","title":"Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks","date":"2024-07-25","arxiv_id":"2407.17697","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-study-of-optimizations-for-fine-tuning","title":"A Study of Optimizations for Fine-tuning Large Language Models","date":"2024-06-04","arxiv_id":"2406.02290","n_code_links":0,"syntology":null},{"paper":null,"slug":"ditto-diffusion-inference-time-t-optimization","title":"DITTO: Diffusion Inference-Time T-Optimization for Music Generation","date":"2024-01-22","arxiv_id":"2401.12179","n_code_links":0,"syntology":null},{"paper":"/paper/capivara-cost-efficient-approach-for","slug":"capivara-cost-efficient-approach-for","title":"CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages","date":"2023-10-20","arxiv_id":"2310.13683","n_code_links":1,"syntology":null},{"paper":null,"slug":"unsupervised-discovery-of-interpretable-4","title":"Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models","date":"2023-10-15","arxiv_id":"2310.09912","n_code_links":0,"syntology":null},{"paper":"/paper/lightseq-sequence-level-parallelism-for","slug":"lightseq-sequence-level-parallelism-for","title":"DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training","date":"2023-10-05","arxiv_id":"2310.03294","n_code_links":1,"syntology":null},{"paper":"/paper/map-memory-aware-automated-intra-op-parallel","slug":"map-memory-aware-automated-intra-op-parallel","title":"Colossal-Auto: Unified Automation of Parallelization and Activation Checkpoint for Large-scale Models","date":"2023-02-06","arxiv_id":"2302.02599","n_code_links":1,"syntology":null},{"paper":"/paper/gleam-greedy-learning-for-large-scale","slug":"gleam-greedy-learning-for-large-scale","title":"GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction","date":"2022-07-18","arxiv_id":"2207.08393","n_code_links":1,"syntology":null},{"paper":"/paper/combined-scaling-for-zero-shot-transfer","slug":"combined-scaling-for-zero-shot-transfer","title":"Combined Scaling for Zero-shot Transfer Learning","date":"2021-11-19","arxiv_id":"2111.10050","n_code_links":0,"syntology":null},{"paper":"/paper/doc2dict-information-extraction-as-text","slug":"doc2dict-information-extraction-as-text","title":"Doc2Dict: Information Extraction as Text Generation","date":"2021-05-16","arxiv_id":"2105.07510","n_code_links":1,"syntology":null},{"paper":"/paper/self-supervised-pretraining-of-visual","slug":"self-supervised-pretraining-of-visual","title":"Self-supervised Pretraining of Visual Features in the Wild","date":"2021-03-02","arxiv_id":"2103.01988","n_code_links":1,"syntology":null},{"paper":"/paper/training-deep-nets-with-sublinear-memory-cost","slug":"training-deep-nets-with-sublinear-memory-cost","title":"Training Deep Nets with Sublinear Memory Cost","date":"2016-04-21","arxiv_id":"1604.06174","n_code_links":6,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}}],"papers_shown":14,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":14,"with_a_code_link":8,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/gradient-checkpointing/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/gradient-checkpointing/papers/ran/1","json":"/method/gradient-checkpointing/papers/ran/1.json","rows":1}],"tasks":[{"task":null,"name":"GPU","papers":7},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/all","name":"All","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/form","name":"Form","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/mri-reconstruction","name":"MRI Reconstruction","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/mamba","name":"Mamba","papers":1},{"task":"/task/model-optimization","name":"Model Optimization","papers":1},{"task":"/task/model-selection","name":"Model Selection","papers":1},{"task":"/task/multi-class-classification","name":"Multi-class Classification","papers":1},{"task":"/task/music-generation","name":"Music Generation","papers":1},{"task":"/task/scheduling","name":"Scheduling","papers":1},{"task":"/task/self-supervised-image-classification","name":"Self-Supervised Image Classification","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2016","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":1},{"year":"2023","papers":4},{"year":"2024","papers":5}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gradient-checkpointing"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Gradient%20Checkpointing","read_at":"2026-10-05T00:57:11+00:00","query":"Gradient Checkpointing","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1604.06174","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Gradient Checkpointing' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["gradient EM","Gradient Cuff","Gradient Mirage","pathway gradient","Gradient Sealing","Gradient Surgery","Gradient Surgery","phantom gradient"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"3b6ec513537dcb0a77669d31383f26fd4d625c0555e37550a7664b149ed0c795","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}