{"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":"/task/neural-network-compression/papers/2","list_of":"/task/neural-network-compression","task":"Neural Network Compression","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":2,"rows_per_page":100,"rows":[101,193],"of":193,"counts":{"archive_papers_tagged":193,"with_a_code_link":77,"where_syntology_ran_a_sample":19,"not_listed_spam_title":0,"listed":193,"listed_where_code_ran":19,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":16,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/neural-network-compression","prev":"/task/neural-network-compression","next":null,"papers":[{"url":null,"slug":"balanced-and-deterministic-weight-sharing-1","title":"Balanced and Deterministic Weight-sharing Helps Network Performance","date":"2023-12-13","arxiv_id":"2312.08401","repositories_listed":0,"syntology":null},{"url":null,"slug":"abkd-graph-neural-network-compression-with","title":"ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation","date":"2023-10-24","arxiv_id":"2310.15938","repositories_listed":0,"syntology":null},{"url":null,"slug":"grokking-as-compression-a-nonlinear","title":"Grokking as Compression: A Nonlinear Complexity Perspective","date":"2023-10-09","arxiv_id":"2310.05918","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-aware-factorization-for-deep","title":"Quantization Aware Factorization for Deep Neural Network Compression","date":"2023-08-08","arxiv_id":"2308.04595","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-computer-vision-techniques-for","title":"Survey on Computer Vision Techniques for Internet-of-Things Devices","date":"2023-08-02","arxiv_id":"2308.02553","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-compression-methods-for-yolov5-a-review","title":"Model Compression Methods for YOLOv5: A Review","date":"2023-07-21","arxiv_id":"2307.11904","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-attribute-localizing-models-for","title":"Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition","date":"2023-06-16","arxiv_id":"2306.09822","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-using-binarization","title":"Neural Network Compression using Binarization and Few Full-Precision Weights","date":"2023-06-15","arxiv_id":"2306.08960","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-neural-network-compression-via","title":"End-to-End Neural Network Compression via $\\frac{\\ell_1}{\\ell_2}$ Regularized Latency Surrogates","date":"2023-06-09","arxiv_id":"2306.05785","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-effect-of-the-long-tail-on","title":"Understanding the Effect of the Long Tail on Neural Network Compression","date":"2023-06-09","arxiv_id":"2306.06238","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-transformers-compressing-transformers","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","date":"2023-06-04","arxiv_id":"2306.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-metrics-for-cnns-compression","title":"Evaluation Metrics for DNNs Compression","date":"2023-05-18","arxiv_id":"2305.10616","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-informative-is-the-approximation-error","title":"How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?","date":"2023-05-09","arxiv_id":"2305.05318","repositories_listed":0,"syntology":null},{"url":null,"slug":"guaranteed-quantization-error-computation-for","title":"Guaranteed Quantization Error Computation for Neural Network Model Compression","date":"2023-04-26","arxiv_id":"2304.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"accerl-policy-acceleration-framework-for-deep","title":"AcceRL: Policy Acceleration Framework for Deep Reinforcement Learning","date":"2022-11-28","arxiv_id":"2211.15023","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixbin-towards-budgeted-binarization","title":"Partial Binarization of Neural Networks for Budget-Aware Efficient Learning","date":"2022-11-12","arxiv_id":"2211.06739","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-by-joint-sparsity","title":"Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction","date":"2022-10-14","arxiv_id":"2210.07451","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-compressions-for-multiplicative","title":"Combining Compressions for Multiplicative Size Scaling on Natural Language Tasks","date":"2022-08-20","arxiv_id":"2208.09684","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantized-sparse-weight-decomposition-for","title":"Quantized Sparse Weight Decomposition for Neural Network Compression","date":"2022-07-22","arxiv_id":"2207.11048","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-neural-network-compression","title":"Quantum Neural Network Compression","date":"2022-07-04","arxiv_id":"2207.01578","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theoretical-understanding-of-neural-network","title":"A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation","date":"2022-06-11","arxiv_id":"2206.05604","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-via-effective","title":"Neural Network Compression via Effective Filter Analysis and Hierarchical Pruning","date":"2022-06-07","arxiv_id":"2206.03596","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-model-quantization","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","date":"2022-05-14","arxiv_id":"2205.07877","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppcd-gan-progressive-pruning-and-class-aware","title":"PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression","date":"2022-03-16","arxiv_id":"2203.08456","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-bisimulation-relations-for-neural","title":"Approximate Bisimulation Relations for Neural Networks and Application to Assured Neural Network Compression","date":"2022-02-02","arxiv_id":"2202.01214","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-compact-parameter-representations-for","title":"Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression","date":"2021-11-19","arxiv_id":"2111.10320","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqn-variable-quantization-noise-for-neural","title":"VQN: Variable Quantization Noise for Neural Network Compression","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-tensor-product-based-tensordecomposition","title":"Semi-tensor Product-based TensorDecomposition for Neural Network Compression","date":"2021-09-30","arxiv_id":"2109.15200","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-compression","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","date":"2021-09-29","arxiv_id":"2109.14710","repositories_listed":0,"syntology":null},{"url":null,"slug":"tropical-geometrical-zonotope-reduction-as","title":"Tropical Geometrical Zonotope Reduction as Applied to Neural Network Compression.","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"quantization-of-generative-adversarial","title":"Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study","date":"2021-08-31","arxiv_id":"2108.13996","repositories_listed":0,"syntology":null},{"url":null,"slug":"dkm-differentiable-k-means-clustering-layer","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","date":"2021-08-28","arxiv_id":"2108.12659","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-the-convergence-of-reinforcement","title":"Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data","date":"2021-07-16","arxiv_id":"2107.08815","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-low-rank-neural-network","title":"Data-Driven Low-Rank Neural Network Compression","date":"2021-07-13","arxiv_id":"2107.05787","repositories_listed":0,"syntology":null},{"url":null,"slug":"hemp-high-order-entropy-minimization-for","title":"HEMP: High-order Entropy Minimization for neural network comPression","date":"2021-07-12","arxiv_id":"2107.05298","repositories_listed":0,"syntology":null},{"url":null,"slug":"minimally-invasive-surgery-for-sparse-neural","title":"Minimally Invasive Surgery for Sparse Neural Networks in Contrastive Manner","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-micro-structured-weight-unification","title":"Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression","date":"2021-06-15","arxiv_id":"2106.08301","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-knowledge-distillation-with-soft","title":"Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis","date":"2021-04-10","arxiv_id":"2104.04868","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-for-noisy-storage","title":"Neural Network Compression for Noisy Storage Devices","date":"2021-02-15","arxiv_id":"2102.07725","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-matrix-products-for-neural-network","title":"Sparse matrix products for neural network compression","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"umec-unified-model-and-embedding-compression","title":"UMEC: Unified model and embedding compression for efficient recommendation systems","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-head-knowledge-distillation-for-model","title":"Multi-head Knowledge Distillation for Model Compression","date":"2020-12-05","arxiv_id":"2012.02911","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-via-sparse","title":"Neural Network Compression Via Sparse Optimization","date":"2020-11-10","arxiv_id":"2011.04868","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-neural-network-compression-for-analog","title":"Noisy Neural Network Compression for Analog Storage Devices","date":"2020-10-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-deep-neural-network-compression","title":"A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions","date":"2020-10-05","arxiv_id":"2010.03954","repositories_listed":0,"syntology":null},{"url":null,"slug":"transform-quantization-for-cnn-compression","title":"Transform Quantization for CNN (Convolutional Neural Network) Compression","date":"2020-09-02","arxiv_id":"2009.01174","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentiable-joint-pruning-and-quantization","title":"Differentiable Joint Pruning and Quantization for Hardware Efficiency","date":"2020-07-20","arxiv_id":"2007.10463","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-tensor-decomposition-in-neural-network","title":"Hybrid Tensor Decomposition in Neural Network Compression","date":"2020-06-29","arxiv_id":"2006.15938","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-gradients-are-lognormally-distributed","title":"Neural gradients are near-lognormal: improved quantized and sparse training","date":"2020-06-15","arxiv_id":"2006.08173","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-networks-compression","title":"Convolutional neural networks compression with low rank and sparse tensor decompositions","date":"2020-06-11","arxiv_id":"2006.06443","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-neural-network-compression","title":"An Overview of Neural Network Compression","date":"2020-06-05","arxiv_id":"2006.03669","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-filter-pruning-criteria-for-deep","title":"Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dp-net-dynamic-programming-guided-deep-neural","title":"DP-Net: Dynamic Programming Guided Deep Neural Network Compression","date":"2020-03-21","arxiv_id":"2003.09615","repositories_listed":0,"syntology":null},{"url":null,"slug":"mint-deep-network-compression-via-mutual","title":"MINT: Deep Network Compression via Mutual Information-based Neuron Trimming","date":"2020-03-18","arxiv_id":"2003.08472","repositories_listed":0,"syntology":null},{"url":null,"slug":"taxonomy-and-evaluation-of-structured","title":"Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks","date":"2019-12-20","arxiv_id":"1912.09802","repositories_listed":0,"syntology":null},{"url":null,"slug":"toco-a-framework-for-compressing-neural","title":"TOCO: A Framework for Compressing Neural Network Models Based on Tolerance Analysis","date":"2019-12-18","arxiv_id":"1912.08792","repositories_listed":0,"syntology":null},{"url":"/paper/lossless-compression-for-3dcnns-based-on","slug":"lossless-compression-for-3dcnns-based-on","title":"Compressing 3DCNNs Based on Tensor Train Decomposition","date":"2019-12-08","arxiv_id":"1912.03647","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-pixel-wise-feature-similarities","title":"Distilling Pixel-Wise Feature Similarities for Semantic Segmentation","date":"2019-10-31","arxiv_id":"1910.14226","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-neural-network","title":"A Comparative Study of Neural Network Compression","date":"2019-10-24","arxiv_id":"1910.11144","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-optimization-framework-for-neural","title":"A Bayesian Optimization Framework for Neural Network Compression","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-normalization-based-quantization-for","title":"Weight Normalization based Quantization for Deep Neural Network Compression","date":"2019-07-01","arxiv_id":"1907.00593","repositories_listed":0,"syntology":null},{"url":null,"slug":"190508318","title":"DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression","date":"2019-05-15","arxiv_id":"1905.08318","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-compression-using-correlation-1","title":"NETWORK COMPRESSION USING CORRELATION ANALYSIS OF LAYER RESPONSES","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scann-synthesis-of-compact-and-accurate","title":"SCANN: Synthesis of Compact and Accurate Neural Networks","date":"2019-04-19","arxiv_id":"1904.09090","repositories_listed":0,"syntology":null},{"url":null,"slug":"cramnet-layer-wise-deep-neural-network","title":"Cramnet: Layer-wise Deep Neural Network Compression with Knowledge Transfer from a Teacher Network","date":"2019-04-11","arxiv_id":"1904.05982","repositories_listed":0,"syntology":null},{"url":"/paper/online-multi-target-regression-trees-with","slug":"online-multi-target-regression-trees-with","title":"Online Multi-target regression trees with stacked leaf models","date":"2019-03-29","arxiv_id":"1903.12483","repositories_listed":0,"syntology":null},{"url":null,"slug":"cascaded-projection-end-to-end-network","title":"Cascaded Projection: End-to-End Network Compression and Acceleration","date":"2019-03-12","arxiv_id":"1903.04988","repositories_listed":0,"syntology":null},{"url":null,"slug":"hardware-guided-symbiotic-training-for","title":"Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM","date":"2019-01-30","arxiv_id":"1901.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-constrained-training-of-deep-neural","title":"Entropy-Constrained Training of Deep Neural Networks","date":"2018-12-18","arxiv_id":"1812.07520","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-identification-of-redundant-kernels","title":"Reliable Identification of Redundant Kernels for Convolutional Neural Network Compression","date":"2018-12-10","arxiv_id":"1812.03608","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-ternary-connect-end-to-end","title":"Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks","date":"2018-11-12","arxiv_id":"1811.04985","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-critical-paths-in-convolutional","title":"Distilling Critical Paths in Convolutional Neural Networks","date":"2018-10-28","arxiv_id":"1811.02643","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-neural-network-compression-via","title":"Efficient Neural Network Compression via Transfer Learning for Industrial Optical Inspection","date":"2018-10-20","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-network-compression-for-aircraft","title":"Deep Neural Network Compression for Aircraft Collision Avoidance Systems","date":"2018-10-09","arxiv_id":"1810.04240","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-compress-or-not-to-compress-understanding","title":"To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression","date":"2018-09-29","arxiv_id":"1810.00208","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlprune-multi-layer-pruning-for-automated","title":"MLPrune: Multi-Layer Pruning for Automated Neural Network Compression","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"2pfpce-two-phase-filter-pruning-based-on","title":"2PFPCE: Two-Phase Filter Pruning Based on Conditional Entropy","date":"2018-09-06","arxiv_id":"1809.02220","repositories_listed":0,"syntology":null},{"url":null,"slug":"constraint-aware-deep-neural-network","title":"Constraint-Aware Deep Neural Network Compression","date":"2018-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coreset-based-neural-network-compression","title":"Coreset-Based Neural Network Compression","date":"2018-07-25","arxiv_id":"1807.09810","repositories_listed":0,"syntology":null},{"url":null,"slug":"network-compression-using-correlation","title":"Filter Distillation for Network Compression","date":"2018-07-20","arxiv_id":"1807.10585","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-neural-network-compression-and","title":"Scalable Neural Network Compression and Pruning Using Hard Clustering and L1 Regularization","date":"2018-06-14","arxiv_id":"1806.05355","repositories_listed":0,"syntology":null},{"url":null,"slug":"mpdcompress-matrix-permutation-decomposition","title":"MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression","date":"2018-05-30","arxiv_id":"1805.12085","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-channel-pruning-method-for-deep","title":"A novel channel pruning method for deep neural network compression","date":"2018-05-29","arxiv_id":"1805.11394","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-compression-for","title":"Convolutional neural network compression for natural language processing","date":"2018-05-28","arxiv_id":"1805.10796","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-compression-using-transform","title":"Neural Network Compression using Transform Coding and Clustering","date":"2018-05-18","arxiv_id":"1805.07258","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-dependent-coresets-for-compressing","title":"Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds","date":"2018-04-15","arxiv_id":"1804.05345","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-network-compression","title":"Adversarial Network Compression","date":"2018-03-28","arxiv_id":"1803.10750","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-deep-neural-network-compression","title":"Universal Deep Neural Network Compression","date":"2018-02-07","arxiv_id":"1802.02271","repositories_listed":0,"syntology":null},{"url":null,"slug":"build-a-compact-binary-neural-network-through","title":"Build a Compact Binary Neural Network through Bit-level Sensitivity and Data Pruning","date":"2018-02-03","arxiv_id":"1802.00904","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-parameter-tying-in-neural-networks","title":"Automatic Parameter Tying in Neural Networks","date":"2018-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-pruning-for-deep-neural-network","title":"Automated Pruning for Deep Neural Network Compression","date":"2017-12-05","arxiv_id":"1712.01721","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinet-a-filter-level-pruning-method-for-deep","title":"ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression","date":"2017-07-20","arxiv_id":"1707.06342","repositories_listed":0,"syntology":null},{"url":null,"slug":"soft-to-hard-vector-quantization-for-end-to","title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","date":"2017-04-03","arxiv_id":"1704.00648","repositories_listed":0,"syntology":null}],"record_sha256":"6e09a3fef7d19975f00f1dd6709e1a4ec1e34fed81ad93f294beff8f7f013b6e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}