{"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/over-parameterization-as-a-catalyst-for","title":"Student Specialization in Deep ReLU Networks With Finite Width and Input Dimension","arxiv_id":"1909.13458","date":"2019-09-30","proceeding":null,"authors":["Yuandong Tian"],"abstract":"We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \\emph{over-realized}: at each layer $l$, the number $n_l$ of student nodes is more than that ($m_l$) of teacher. Under mild conditions on dataset and teacher network, we prove that when the gradient is small at every data sample, each teacher node is \\emph{specialized} by at least one student node \\emph{at the lowest layer}. For two-layer network, such specialization can be achieved by training on any dataset of \\emph{polynomial} size $\\mathcal{O}( K^{5/2} d^3 \\epsilon^{-1})$. until the gradient magnitude drops to $\\mathcal{O}(\\epsilon/K^{3/2}\\sqrt{d})$. Here $d$ is the input dimension, $K = m_1 + n_1$ is the total number of neurons in the lowest layer of teacher and student. Note that we require a specific form of data augmentation and the sample complexity includes the additional data generated from augmentation. To our best knowledge, we are the first to give polynomial sample complexity for student specialization of training two-layer (Leaky) ReLU networks with finite depth and width in teacher-student setting, and finite complexity for the lowest layer specialization in multi-layer case, without parametric assumption of the input (like Gaussian). Our theory suggests that teacher nodes with large fan-out weights get specialized first when the gradient is still large, while others are specialized with small gradient, which suggests inductive bias in training. This shapes the stage of training as empirically observed in multiple previous works. Experiments on synthetic and CIFAR10 verify our findings. The code is released in https://github.com/facebookresearch/luckmatters.","url_abs":"https://arxiv.org/abs/1909.13458v6","url_pdf":"https://arxiv.org/pdf/1909.13458v6.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":"over-parameterization-as-a-catalyst-for","repo_url":"https://github.com/facebookresearch/luckmatters","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"facebookresearch/luckmatters","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":5,"harvested_for":["1905.13405","2010.00578","2102.06810","2310.00535","2410.01779"],"harvested_for_calls":[{"arxiv_id":"1905.13405","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1905.13405"},"call":"get_harvested_code_for_paper(arxiv_id=\"1905.13405\")"},{"arxiv_id":"2010.00578","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.00578"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.00578\")"},{"arxiv_id":"2102.06810","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.06810"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.06810\")"},{"arxiv_id":"2310.00535","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.00535"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.00535\")"},{"arxiv_id":"2410.01779","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.01779"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.01779\")"}]}],"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":"dbede609cea4c315aeb4856aa631c70574d25829de3fdbf9c35051776a8502e1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}