{"total":29,"rows":[{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","created":"2021-08-13","cited_by_count":80,"area":null},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2106.15739","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","created":"2021-06-29","cited_by_count":20,"area":null},{"id":"2510.19093","title":"Weight Decay may matter more than muP for Learning Rate Transfer in Practice","created":"2025-10-21","cited_by_count":20,"area":null},{"id":"2209.03695","title":"Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes","created":"2022-09-08","cited_by_count":19,"area":null},{"id":"2101.07525","title":"Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning","created":"2021-01-19","cited_by_count":14,"area":null},{"id":"2210.15898","title":"Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis","created":"2022-10-28","cited_by_count":13,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2508.01483","title":"Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler","created":"2025-08-02","cited_by_count":12,"area":null},{"id":"2106.04413","title":"Stochastic Whitening Batch Normalization","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2203.10778","title":"Delving into the Estimation Shift of Batch Normalization in a Network","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"area":null},{"id":"2206.14098","title":"RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2102.11855","title":"Deep Unitary Convolutional Neural Networks","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2305.17205","title":"Ghost Noise for Regularizing Deep Neural Networks","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2504.16020","title":"AlphaGrad: Non-Linear Gradient Normalization Optimizer","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2607.21005","title":"Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2102.10052","title":"A Projection Algorithm for the Unitary Weights","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2210.10725","title":"SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction","created":"2022-10-09","cited_by_count":0,"area":null},{"id":"2311.15993","title":"Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2601.08166","title":"ZeroDVFS: Zero-Shot LLM-Guided Core and Frequency Allocation for Embedded Platforms","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2609.09116","title":"When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}