{"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":"/paper/do-we-actually-need-dense-over","title":"Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training","arxiv_id":"2102.02887","date":"2021-02-04","proceeding":null,"authors":["Shiwei Liu","Lu Yin","Decebal Constantin Mocanu","Mykola Pechenizkiy"],"abstract":"In this paper, we introduce a new perspective on training deep neural networks capable of state-of-the-art performance without the need for the expensive over-parameterization by proposing the concept of In-Time Over-Parameterization (ITOP) in sparse training. By starting from a random sparse network and continuously exploring sparse connectivities during training, we can perform an Over-Parameterization in the space-time manifold, closing the gap in the expressibility between sparse training and dense training. We further use ITOP to understand the underlying mechanism of Dynamic Sparse Training (DST) and indicate that the benefits of DST come from its ability to consider across time all possible parameters when searching for the optimal sparse connectivity. As long as there are sufficient parameters that have been reliably explored during training, DST can outperform the dense neural network by a large margin. We present a series of experiments to support our conjecture and achieve the state-of-the-art sparse training performance with ResNet-50 on ImageNet. More impressively, our method achieves dominant performance over the overparameterization-based sparse methods at extreme sparsity levels. When trained on CIFAR-100, our method can match the performance of the dense model even at an extreme sparsity (98%). Code can be found https://github.com/Shiweiliuiiiiiii/In-Time-Over-Parameterization.","url_abs":"https://arxiv.org/abs/2102.02887v3","url_pdf":"https://arxiv.org/pdf/2102.02887v3.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":"do-we-actually-need-dense-over","repo_url":"https://github.com/Shiweiliuiiiiiii/GraNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"do-we-actually-need-dense-over","repo_url":"https://github.com/Shiweiliuiiiiiii/In-Time-Over-Parameterization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"do-we-actually-need-dense-over","repo_url":"https://github.com/stevenboys/agent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"do-we-actually-need-dense-over","repo_url":"https://github.com/vita-group/granet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"sparse-learning","task_name":"Sparse Learning"}],"methods":[{"method_slug":"dst","method_name":"DST"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sparse-learning-on-imagenet","task":"Sparse Learning","dataset":"ImageNet","model":"Resnet-50: 80% Sparse 100 epochs","rank_in_archive_order":4,"of":9,"metrics":{"Top-1 Accuracy":"75.84"},"uses_additional_data":false},{"leaderboard":"/sota/sparse-learning-on-imagenet","task":"Sparse Learning","dataset":"ImageNet","model":"Resnet-50: 90% Sparse 100 epochs","rank_in_archive_order":6,"of":9,"metrics":{"Top-1 Accuracy":"73.82"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.02887","atlas_url":"https://app.syntology.ai/?focus=2102.02887","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2102.02887"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.02887\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.02887"},"call":"get_concepts_for_paper(arxiv_id=\"2102.02887\")"}],"by_repo":[{"repo":"Shiweiliuiiiiiii/GraNet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Shiweiliuiiiiiii/In-Time-Over-Parameterization","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"stevenboys/agent","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vita-group/granet","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2106.10404"],"harvested_for_calls":[{"arxiv_id":"2106.10404","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.10404"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.10404\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"66c4d9c1af7d063d4aa8746b39a208d2c429a61bc679cdddf741ab151399162e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}