{"total":40,"rows":[{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161,"area":null},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155,"area":null},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2404.11735","title":"Learning with 3D rotations, a hitchhiker's guide to SO(3)","created":"2024-04-17","cited_by_count":42,"area":null},{"id":"2306.04815","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2212.13827","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","created":"2022-12-28","cited_by_count":28,"area":null},{"id":"2405.11272","title":"Double Correction Framework for Denoising Recommendation","created":"2024-05-18","cited_by_count":19,"area":null},{"id":"2405.12807","title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","created":"2024-05-21","cited_by_count":18,"area":null},{"id":"2302.09178","title":"Improving Training Stability for Multitask Ranking Models in Recommender Systems","created":"2023-02-17","cited_by_count":13,"area":null},{"id":"2210.05956","title":"Towards Theoretically Inspired Neural Initialization Optimization","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2302.01952","title":"On a continuous time model of gradient descent dynamics and instability in deep learning","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2302.05823","title":"Data efficiency and extrapolation trends in neural network interatomic potentials","created":"2023-02-12","cited_by_count":10,"area":null},{"id":"2405.02803","title":"Is Flash Attention Stable?","created":"2024-05-05","cited_by_count":10,"area":null},{"id":"2407.06183","title":"Stepping on the Edge: Curvature Aware Learning Rate Tuners","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2409.07787","title":"Stable Language Model Pre-training by Reducing Embedding Variability","created":"2024-09-12","cited_by_count":6,"area":null},{"id":"2604.20446","title":"The Origin of Edge of Stability","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2202.04509","title":"Optimal learning rate schedules in high-dimensional non-convex optimization problems","created":"2022-02-09","cited_by_count":4,"area":null},{"id":"2402.00853","title":"LTAU-FF: Loss Trajectory Analysis for Uncertainty in Atomistic Force Fields","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2301.12589","title":"Confidence-Aware Calibration and Scoring Functions for Curriculum Learning","created":"2023-01-29","cited_by_count":2,"area":null},{"id":"2410.05806","title":"A Parameter Update Balancing Algorithm for Multi-task Ranking Models in Recommendation Systems","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2412.18790","title":"Torque-Aware Momentum","created":"2024-12-25","cited_by_count":2,"area":null},{"id":"2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2602.03001","title":"Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2304.11692","title":"The Disharmony between BN and ReLU Causes Gradient Explosion, but is Offset by the Correlation between Activations","created":"2023-04-23","cited_by_count":1,"area":null},{"id":"2401.08830","title":"Stochastic Subnetwork Annealing: A Regularization Technique for Fine Tuning Pruned Subnetworks","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2409.16668","title":"Topic-aware Causal Intervention for Counterfactual Detection","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2512.13728","title":"CurvaDion: Curvature-Adaptive Distributed Orthonormalization","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2305.18820","title":"Robust Reinforcement Learning Objectives for Sequential Recommender Systems","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2402.12418","title":"Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2407.19044","title":"Advancing Neural Network Performance through Emergence-Promoting Initialization Scheme","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2511.16717","title":"A Machine Learning-Driven Solution for Denoising Inertial Confinement Fusion Images","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2603.10301","title":"What do near-optimal learning rate schedules look like?","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2606.16768","title":"Taming Curvature: Architecture Warm-Up for Stable Transformer Training","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.26492","title":"Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.33041","title":"Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.14394","title":"Understanding and Mitigating Training Instability in Large-Scale Recommender Systems: A Cascade Perspective","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}