{"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/deep-learning-and-the-information-bottleneck","title":"Deep Learning and the Information Bottleneck Principle","arxiv_id":"1503.02406","date":"2015-03-09","proceeding":null,"authors":["Naftali Tishby","Noga Zaslavsky"],"abstract":"Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the\ninformation bottleneck (IB) principle. We first show that any DNN can be\nquantified by the mutual information between the layers and the input and\noutput variables. Using this representation we can calculate the optimal\ninformation theoretic limits of the DNN and obtain finite sample generalization\nbounds. The advantage of getting closer to the theoretical limit is\nquantifiable both by the generalization bound and by the network's simplicity.\nWe argue that both the optimal architecture, number of layers and\nfeatures/connections at each layer, are related to the bifurcation points of\nthe information bottleneck tradeoff, namely, relevant compression of the input\nlayer with respect to the output layer. The hierarchical representations at the\nlayered network naturally correspond to the structural phase transitions along\nthe information curve. We believe that this new insight can lead to new\noptimality bounds and deep learning algorithms.","url_abs":"http://arxiv.org/abs/1503.02406v1","url_pdf":"http://arxiv.org/pdf/1503.02406v1.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":"deep-learning-and-the-information-bottleneck","repo_url":"https://github.com/ChenLiu-1996/DiffusionSpectralEntropy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-learning-and-the-information-bottleneck","repo_url":"https://github.com/amrutn/Information-in-Language","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"generalization-bounds","task_name":"Generalization Bounds"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1503.02406","atlas_url":"https://app.syntology.ai/?focus=1503.02406","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":"1503.02406"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1503.02406\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1503.02406"},"call":"get_concepts_for_paper(arxiv_id=\"1503.02406\")"}],"by_repo":[{"repo":"ChenLiu-1996/DiffusionSpectralEntropy","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2312.04823"],"harvested_for_calls":[{"arxiv_id":"2312.04823","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2312.04823"},"call":"get_harvested_code_for_paper(arxiv_id=\"2312.04823\")"}]},{"repo":"amrutn/Information-in-Language","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"8bc021a357088991db30bf871db346e25c2d1086c06dc6701f633ce92bdf5b98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}