{"total":35,"rows":[{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"area":null},{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2507.02119","title":"Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks","created":"2025-07-02","cited_by_count":22,"area":null},{"id":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2510.01098","title":"Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time","created":"2025-10-01","cited_by_count":16,"area":null},{"id":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2410.04642","title":"The Optimization Landscape of SGD Across the Feature Learning Strength","created":"2024-10-06","cited_by_count":13,"area":null},{"id":"2409.13904","title":"High-dimensional learning of narrow neural networks","created":"2024-09-20","cited_by_count":12,"area":null},{"id":"2506.05249","title":"On the Convergence of Gradient Descent on Learning Transformers with Residual Connections","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2506.16884","title":"The Importance of Being Lazy: Scaling Limits of Continual Learning","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2605.07870","title":"Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer","created":"2026-05-08","cited_by_count":6,"area":null},{"id":"2410.23610","title":"Global Convergence in Training Large-Scale Transformers","created":"2024-10-31","cited_by_count":5,"area":null},{"id":"2506.00846","title":"Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2502.17405","title":"Function-Space Learning Rates","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2506.01582","title":"Bayes optimal learning of attention-indexed models","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2604.27077","title":"Learning Rate Transfer in Normalized Transformers","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2510.01930","title":"Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2602.07697","title":"On the Infinite Width and Depth Limits of Predictive Coding Networks","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2605.21486","title":"Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2606.20299","title":"Statistical Properties of Training & Generalization","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2510.06685","title":"Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2601.16514","title":"Finite-Time Analysis of Gradient Descent for Shallow Transformers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2605.10775","title":"On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2503.23982","title":"Deep Neural Nets as Hamiltonians","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2506.10371","title":"Revisiting Transformers with Insights from Image Filtering and Boosting","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2509.18997","title":"Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2602.10209","title":"Neural Network Quantum Field Theory from Transformer Architectures","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2605.12697","title":"A Unified Framework for Critical Scaling of Inverse Temperature in Self-Attention","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2607.07884","title":"Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.15239","title":"Learning reshapes power-law anisotropy in internal representations","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}