{"total":57,"rows":[{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2104.00903","title":"Network Quantization with Element-wise Gradient Scaling","created":"2021-04-02","cited_by_count":87,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55,"area":null},{"id":"2109.15103","title":"Scalable Rule-Based Representation Learning for Interpretable Classification","created":"2021-09-30","cited_by_count":40,"area":null},{"id":"2211.07091","title":"BiViT: Extremely Compressed Binary Vision Transformer","created":"2022-11-14","cited_by_count":28,"area":null},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2308.06689","title":"Estimator Meets Equilibrium Perspective: A Rectified Straight Through Estimator for Binary Neural Networks Training","created":"2023-08-13","cited_by_count":19,"area":null},{"id":"2310.14336","title":"Learning Interpretable Rules for Scalable Data Representation and Classification","created":"2023-10-22","cited_by_count":14,"area":null},{"id":"2110.13220","title":"Demystifying and Generalizing BinaryConnect","created":"2021-10-25","cited_by_count":11,"area":null},{"id":"2112.02880","title":"AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2503.06862","title":"FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2205.14107","title":"Spartan: Differentiable Sparsity via Regularized Transportation","created":"2022-05-27","cited_by_count":8,"area":null},{"id":"2112.02612","title":"Training Structured Neural Networks Through Manifold Identification and Variance Reduction","created":"2021-12-05","cited_by_count":7,"area":null},{"id":"2205.12918","title":"A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps","created":"2022-05-25","cited_by_count":6,"area":null},{"id":"2307.03936","title":"Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives","created":"2023-07-08","cited_by_count":5,"area":null},{"id":"2312.04311","title":"Finding Interpretable Class-Specific Patterns through Efficient Neural Search","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.15748","title":"PARQ: Piecewise-Affine Regularized Quantization","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2302.03390","title":"Learning Discretized Neural Networks under Ricci Flow","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2402.17710","title":"Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2510.18784","title":"CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2102.11786","title":"QuPeL: Quantized Personalization with Applications to Federated Learning","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2110.05850","title":"Improving Binary Neural Networks through Fully Utilizing Latent Weights","created":"2021-10-12","cited_by_count":3,"area":null},{"id":"2310.15128","title":"Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2405.16339","title":"BOLD: Boolean Logic Deep Learning","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2210.03069","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2211.03741","title":"AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2303.01505","title":"Ternary Quantization: A Survey","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2402.06606","title":"RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2404.19248","title":"Scheduling Weight Transitions for Quantization-Aware Training","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2107.01400","title":"Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations","created":"2021-07-03","cited_by_count":1,"area":null},{"id":"2211.13838","title":"Signed Binary Weight Networks","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2301.06193","title":"RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNs","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2306.17266","title":"Subgraph Stationary Hardware-Software Inference Co-Design","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2502.01908","title":"Physics-Inspired Binary Neural Networks: Interpretable Compression with Theoretical Guarantees","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2502.21099","title":"Adaptive Lipschitz-Free Proximal Gradient Methods for Stochastic Composite Nonconvex Optimization","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2507.04456","title":"BiVM: Accurate Binarized Neural Network for Efficient Video Matting","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2606.09012","title":"Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2206.06531","title":"A Stochastic Proximal Method for Nonsmooth Regularized Finite Sum Optimization","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2212.12649","title":"Hyperspherical Loss-Aware Ternary Quantization","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2312.01581","title":"PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-Off","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2402.05033","title":"Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2503.01639","title":"Cauchy-Schwarz Regularizers","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2506.20927","title":"Interpretable Representation Learning for Additive Rule Ensembles","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2508.11112","title":"Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2510.18218","title":"DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2601.22660","title":"Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.05994","title":"DiBA: Diagonal and Binary Matrix Approximation for Neural Network Weight Compression","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.27759","title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.14630","title":"Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.11240","title":"VQ-bench: A Composable Vector Quantization Framework","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.06430","title":"Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}