{"list":"other","total":56,"rows":[{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"1602.07868","title":"Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks","created":"2016-02-25","cited_by_count":543},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"2312.02696","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","created":"2023-12-05","cited_by_count":402},{"id":"1502.02551","title":"Deep Learning with Limited Numerical Precision","created":"2015-02-09","cited_by_count":376},{"id":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192},{"id":"2402.04291","title":"BiLLM: Pushing the Limit of Post-Training Quantization for LLMs","created":"2024-02-06","cited_by_count":144},{"id":"1706.05350","title":"L2 Regularization versus Batch and Weight Normalization","created":"2017-06-16","cited_by_count":124},{"id":"1910.07454","title":"An Exponential Learning Rate Schedule for Deep Learning","created":"2019-10-16","cited_by_count":121},{"id":"1810.12281","title":"Three Mechanisms of Weight Decay Regularization","created":"2018-10-29","cited_by_count":113},{"id":"2310.17813","title":"A Spectral Condition for Feature Learning","created":"2023-10-26","cited_by_count":109},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86},{"id":"2410.06511","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","created":"2024-10-09","cited_by_count":85},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77},{"id":"2310.04415","title":"Why Do We Need Weight Decay in Modern Deep Learning?","created":"2023-10-06","cited_by_count":72},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70},{"id":"2010.02916","title":"Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate","created":"2020-10-06","cited_by_count":59},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53},{"id":"2310.05898","title":"Lion Secretly Solves Constrained Optimization: As Lyapunov Predicts","created":"2023-10-09","cited_by_count":51},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46},{"id":"1804.08071","title":"Decoupled Networks","created":"2018-04-22","cited_by_count":45},{"id":"2011.11152","title":"On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective","created":"2020-11-23","cited_by_count":25},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","cited_by_count":23},{"id":"2506.03595","title":"Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner","created":"2025-06-04","cited_by_count":23},{"id":"2410.23922","title":"Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training","created":"2024-10-31","cited_by_count":22},{"id":"2506.02285","title":"Why Gradients Rapidly Increase Near the End of Training","created":"2025-06-02","cited_by_count":22},{"id":"2412.13148","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","created":"2024-12-17","cited_by_count":20},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20},{"id":"2403.09635","title":"Transformers Get Stable: An End-to-End Signal Propagation Theory for Language Models","created":"2024-03-14","cited_by_count":18},{"id":"2010.06192","title":"Revisiting BFloat16 Training","created":"2020-10-13","cited_by_count":17},{"id":"2511.18890","title":"Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models","created":"2025-11-24","cited_by_count":15},{"id":"2506.16659","title":"Memory-Efficient LLM Pretraining via Minimalist Optimizer Design","created":"2025-06-20","cited_by_count":13},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12},{"id":"2603.09952","title":"On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer","created":"2026-03-10","cited_by_count":12},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10},{"id":"2502.20566","title":"Stochastic Rounding for LLM Training: Theory and Practice","created":"2025-02-27","cited_by_count":10},{"id":"2603.14315","title":"Enhancing LLM Training via Spectral Clipping","created":"2026-03-15","cited_by_count":10},{"id":"2502.06742","title":"Gradient Multi-Normalization for Stateless and Scalable LLM Training","created":"2025-02-10","cited_by_count":9},{"id":"2601.21487","title":"Manifold constrained steepest descent for smooth and closed-set optimization","created":"2026-01-29","cited_by_count":8},{"id":"2602.09314","title":"Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory","created":"2026-02-10","cited_by_count":8},{"id":"2504.10770","title":"Collaborative Bayesian Optimization via Wasserstein Barycenters","created":"2025-04-15","cited_by_count":7},{"id":"2602.03839","title":"Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL","created":"2026-02-03","cited_by_count":7},{"id":"2502.02332","title":"Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning","created":"2025-02-04","cited_by_count":6},{"id":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4},{"id":"2405.07083","title":"Data-Efficient and Robust Task Selection for Meta-Learning","created":"2024-05-11","cited_by_count":2}],"next_cursor":null}