{"url":"/task/neural-network-compression","name":"Neural Network Compression","slug":"neural-network-compression","description_markdown":null,"categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Playing Games","url":"/area/playing-games"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":193,"papers_with_code":77,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/neural-network-compression-on-cifar-10","slug":"neural-network-compression-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":5,"metrics":["Size (MB)"],"first_row_in_archive_order":{"model":"ShuffleNet – Quantised","paper_title":"Quantisation and Pruning for Neural Network Compression and Regularisation","paper_url":"/paper/quantisation-and-pruning-for-neural-network","paper_date":"2020-01-14","arxiv_id":"2001.04850","code_links":[{"title":"kpaupamah/compression-and-regularisation","url":"https://github.com/kpaupamah/compression-and-regularisation"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145}],"subtasks":[],"parent_tasks":[{"url":"/task/2d-classification","name":"2D Classification"},{"url":"/task/model-compression","name":"Model Compression"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":77,"tagged_in_all":193,"items":[{"url":"/paper/nerv-neural-representations-for-videos","title":"NeRV: Neural Representations for Videos","date":"2021-10-26","arxiv_id":"2110.13903","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/zeroq-a-novel-zero-shot-quantization","title":"ZeroQ: A Novel Zero Shot Quantization Framework","date":"2020-01-01","arxiv_id":"2001.00281","repositories_listed":3,"syntology":{"n":19,"n_ran":4,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/learning-filter-basis-for-convolutional","title":"Learning Filter Basis for Convolutional Neural Network Compression","date":"2019-08-23","arxiv_id":"1908.08932","repositories_listed":3,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/data-free-learning-of-student-networks","title":"Data-Free Learning of Student Networks","date":"2019-04-02","arxiv_id":"1904.01186","repositories_listed":3,"syntology":null},{"url":"/paper/one-time-is-not-enough-iterative-tensor","title":"MUSCO: Multi-Stage Compression of neural networks","date":"2019-03-24","arxiv_id":"1903.09973","repositories_listed":3,"syntology":null},{"url":"/paper/improving-neural-network-quantization-without","title":"Improving Neural Network Quantization without Retraining using Outlier Channel Splitting","date":"2019-01-28","arxiv_id":"1901.09504","repositories_listed":3,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/soft-weight-sharing-for-neural-network","title":"Soft Weight-Sharing for Neural Network Compression","date":"2017-02-13","arxiv_id":"1702.04008","repositories_listed":3,"syntology":null},{"url":"/paper/sparsity-by-redundancy-solving-l-1-with-a","title":"spred: Solving $L_1$ Penalty with SGD","date":"2022-10-03","arxiv_id":"2210.01212","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/few-bit-backward-quantized-gradients-of","title":"Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction","date":"2022-02-01","arxiv_id":"2202.00441","repositories_listed":2,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/head-network-distillation-splitting-distilled","title":"Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-Constrained Edge Computing Systems","date":"2020-11-20","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/teacher-class-network-a-neural-network","title":"Teacher-Class Network: A Neural Network Compression Mechanism","date":"2020-04-07","arxiv_id":"2004.03281","repositories_listed":2,"syntology":null},{"url":"/paper/neural-network-compression-framework-for-fast","title":"Neural Network Compression Framework for fast model inference","date":"2020-02-20","arxiv_id":"2002.08679","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/the-continuous-categorical-a-novel-simplex","title":"The continuous categorical: a novel simplex-valued exponential family","date":"2020-02-20","arxiv_id":"2002.08563","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/distilled-split-deep-neural-networks-for-edge","title":"Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems","date":"2019-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/ir-net-forward-and-backward-information","title":"Forward and Backward Information Retention for Accurate Binary Neural Networks","date":"2019-09-24","arxiv_id":"1909.10788","repositories_listed":2,"syntology":null},{"url":"/paper/learning-sparse-networks-using-targeted","title":"Learning Sparse Networks Using Targeted Dropout","date":"2019-05-31","arxiv_id":"1905.13678","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/ecc-energy-constrained-deep-neural-network","title":"ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model","date":"2018-12-05","arxiv_id":"1812.01803","repositories_listed":2,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/pruning-neural-networks-is-it-time-to-nip-it","title":"A Closer Look at Structured Pruning for Neural Network Compression","date":"2018-10-10","arxiv_id":"1810.04622","repositories_listed":2,"syntology":null},{"url":"/paper/minimal-random-code-learning-getting-bits","title":"Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters","date":"2018-09-30","arxiv_id":"1810.00440","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/weightless-lossy-weight-encoding-for-deep","title":"Weightless: Lossy Weight Encoding For Deep Neural Network Compression","date":"2017-11-13","arxiv_id":"1711.04686","repositories_listed":2,"syntology":null},{"url":"/paper/diversity-networks-neural-network-compression","title":"Diversity Networks: Neural Network Compression Using Determinantal Point Processes","date":"2015-11-16","arxiv_id":"1511.05077","repositories_listed":2,"syntology":null},{"url":"/paper/certified-neural-approximations-of-nonlinear","title":"Certified Neural Approximations of Nonlinear Dynamics","date":"2025-05-21","arxiv_id":"2505.15497","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-zero-shot-lossless","title":"Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models","date":"2024-09-26","arxiv_id":"2409.17836","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/torch2chip-an-end-to-end-customizable-deep","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","date":"2024-05-02","arxiv_id":"2405.01775","repositories_listed":1,"syntology":null},{"url":"/paper/towards-meta-pruning-via-optimal-transport","title":"Towards Meta-Pruning via Optimal Transport","date":"2024-02-12","arxiv_id":"2402.07839","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/causal-dfq-causality-guided-data-free-network","title":"Causal-DFQ: Causality Guided Data-free Network Quantization","date":"2023-09-24","arxiv_id":"2309.13682","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-deep-neural-network-pruning","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","date":"2023-08-13","arxiv_id":"2308.06767","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-compressibility-of-overparametrized","title":"Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD","date":"2023-06-13","arxiv_id":"2306.08125","repositories_listed":1,"syntology":null},{"url":"/paper/vector-valued-variation-spaces-and-width","title":"Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression","date":"2023-05-25","arxiv_id":"2305.16534","repositories_listed":1,"syntology":null},{"url":"/paper/swifttron-an-efficient-hardware-accelerator","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","date":"2023-04-08","arxiv_id":"2304.03986","repositories_listed":1,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}