{"total":42,"rows":[{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2210.00965","title":"Green Learning: Introduction, Examples and Outlook","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2310.04400","title":"On the Embedding Collapse when Scaling up Recommendation Models","created":"2023-10-06","cited_by_count":29,"area":null},{"id":"2102.07156","title":"ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations","created":"2021-02-14","cited_by_count":21,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2206.05794","title":"SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network","created":"2022-06-12","cited_by_count":19,"area":null},{"id":"2205.11921","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","created":"2022-05-24","cited_by_count":16,"area":null},{"id":"2109.14710","title":"Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition","created":"2021-09-29","cited_by_count":14,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2107.14444","title":"Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN","created":"2021-07-30","cited_by_count":9,"area":null},{"id":"2206.03927","title":"Boundary between noise and information applied to filtering neural network weight matrices","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2402.04051","title":"Analysis of Linear Mode Connectivity via Permutation-Based Weight Matching: With Insights into Other Permutation Search Methods","created":"2024-02-06","cited_by_count":9,"area":null},{"id":"2201.06776","title":"Pruning-aware Sparse Regularization for Network Pruning","created":"2022-01-18","cited_by_count":5,"area":null},{"id":"2303.13635","title":"Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training","created":"2023-03-22","cited_by_count":5,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2306.02433","title":"Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation","created":"2023-06-04","cited_by_count":4,"area":null},{"id":"2410.11985","title":"The Fair Language Model Paradox","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2107.04380","title":"Model compression as constrained optimization, with application to neural nets. Part V: combining compressions","created":"2021-07-09","cited_by_count":3,"area":null},{"id":"2204.05566","title":"Compact Model Training by Low-Rank Projection with Energy Transfer","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2308.13157","title":"Federated Learning in IoT: a Survey from a Resource-Constrained Perspective","created":"2023-08-25","cited_by_count":2,"area":null},{"id":"2410.02176","title":"Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2111.15179","title":"A Highly Effective Low-Rank Compression of Deep Neural Networks with Modified Beam-Search and Modified Stable Rank","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2205.15198","title":"STN: Scalable Tensorizing Networks via Structure-Aware Training and Adaptive Compression","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2309.13077","title":"A Differentiable Framework for End-to-End Learning of Hybrid Structured Compression","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.12688","title":"Compression of Recurrent Neural Networks using Matrix Factorization","created":"2023-10-19","cited_by_count":1,"area":null},{"id":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.04485","title":"Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.09816","title":"CompSplat: Compression-aware 3D Gaussian Splatting for Real-world Video","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2105.10436","title":"Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning","created":"2021-05-21","cited_by_count":0,"area":null},{"id":"2107.10998","title":"Pruning Ternary Quantization","created":"2021-07-23","cited_by_count":0,"area":null},{"id":"2110.05954","title":"Mining the Weights Knowledge for Optimizing Neural Network Structures","created":"2021-10-11","cited_by_count":0,"area":null},{"id":"2110.08679","title":"An Acceleration Method Based on Deep Learning and Multilinear Feature Space","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2210.06299","title":"SeKron: A Decomposition Method Supporting Many Factorization Structures","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2212.12651","title":"Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuning","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2308.02553","title":"Survey on Computer Vision Techniques for Internet-of-Things Devices","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2309.15881","title":"Enhancing Cross-Category Learning in Recommendation Systems with Multi-Layer Embedding Training","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2504.12471","title":"You Don't Need All Attentions: Distributed Dynamic Fine-Tuning for Foundation Models","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.16965","title":"RocketStack: Level-aware Deep Recursive Ensemble Learning Architecture","created":"2025-06-20","cited_by_count":0,"area":null}],"next_cursor":null}