{"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/delta-stn-efficient-bilevel-optimization-for","title":"Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians","arxiv_id":"2010.13514","date":"2020-10-26","proceeding":"NeurIPS 2020 12","authors":["Juhan Bae","Roger Grosse"],"abstract":"Hyperparameter optimization of neural networks can be elegantly formulated as a bilevel optimization problem. While research on bilevel optimization of neural networks has been dominated by implicit differentiation and unrolling, hypernetworks such as Self-Tuning Networks (STNs) have recently gained traction due to their ability to amortize the optimization of the inner objective. In this paper, we diagnose several subtle pathologies in the training of STNs. Based on these observations, we propose the $\\Delta$-STN, an improved hypernetwork architecture which stabilizes training and optimizes hyperparameters much more efficiently than STNs. The key idea is to focus on accurately approximating the best-response Jacobian rather than the full best-response function; we achieve this by reparameterizing the hypernetwork and linearizing the network around the current parameters. We demonstrate empirically that our $\\Delta$-STN can tune regularization hyperparameters (e.g. weight decay, dropout, number of cutout holes) with higher accuracy, faster convergence, and improved stability compared to existing approaches.","url_abs":"https://arxiv.org/abs/2010.13514v1","url_pdf":"https://arxiv.org/pdf/2010.13514v1.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":"delta-stn-efficient-bilevel-optimization-for","repo_url":"https://github.com/pomonam/Self-Tuning-Networks","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"bilevel-optimization","task_name":"Bilevel Optimization"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"}],"methods":[{"method_slug":"cutout","method_name":"Cutout"},{"method_slug":"dropconnect","method_name":"DropConnect"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"},{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.13514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13514"}},"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/pomonam/Self-Tuning-Networks","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"fed94e0840cc8cf9","entry":"StnConv2d","repo":"pomonam/Self-Tuning-Networks","repo_kind":"official","path":"layers/conv2d.py","file_url":"https://github.com/pomonam/Self-Tuning-Networks/blob/HEAD/layers/conv2d.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fed94e0840cc8cf9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}