{"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/deephoyer-learning-sparser-neural-network","title":"DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures","arxiv_id":"1908.09979","date":"2019-08-27","proceeding":"ICLR 2020 1","authors":["Huanrui Yang","Wei Wen","Hai Li"],"abstract":"In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter sparsity directly and is invariant to the scaling of parameter values, but it cannot provide useful gradients, and therefore requires complex optimization techniques. The L1 regularizer is almost everywhere differentiable and can be easily optimized with gradient descent. Yet it is not scale-invariant, causing the same shrinking rate to all parameters, which is inefficient in increasing sparsity. Inspired by the Hoyer measure (the ratio between L1 and L2 norms) used in traditional compressed sensing problems, we present DeepHoyer, a set of sparsity-inducing regularizers that are both differentiable almost everywhere and scale-invariant. Our experiments show that enforcing DeepHoyer regularizers can produce even sparser neural network models than previous works, under the same accuracy level. We also show that DeepHoyer can be applied to both element-wise and structural pruning.","url_abs":"https://arxiv.org/abs/1908.09979v2","url_pdf":"https://arxiv.org/pdf/1908.09979v2.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":"deephoyer-learning-sparser-neural-network","repo_url":"https://github.com/yanghr/DeepHoyer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"efficient-neural-network","task_name":"Efficient Neural Network"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.09979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09979"}},"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/yanghr/DeepHoyer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"cifar/models/cifar/preresnet.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/cifar/models/cifar/preresnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"80752954f2a868b8","entry":"accuracy","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/main_group.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/main_group.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80752954f2a868b8"}},{"code_sha256_prefix":"eae15ffc6073381c","entry":"test","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/util.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eae15ffc6073381c"}},{"code_sha256_prefix":"396b51c81635919d","entry":"train","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/main_group.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/main_group.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"396b51c81635919d"}},{"code_sha256_prefix":"eb96629937f51120","entry":"train","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/prun_tune.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/prun_tune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb96629937f51120"}},{"code_sha256_prefix":"6184b69dc55e090b","entry":"validate","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/main_group.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/main_group.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6184b69dc55e090b"}},{"code_sha256_prefix":"77a263b87d5243b1","entry":"validate","repo":"yanghr/DeepHoyer","repo_kind":"official","path":"imagenet/prun_tune.py","file_url":"https://github.com/yanghr/DeepHoyer/blob/HEAD/imagenet/prun_tune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77a263b87d5243b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}