{"total":54,"rows":[{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193,"area":null},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2506.04192","title":"Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise","created":"2025-06-04","cited_by_count":41,"area":null},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","cited_by_count":36,"area":null},{"id":"2406.10650","title":"The Implicit Bias of Adam on Separable Data","created":"2024-06-15","cited_by_count":36,"area":null},{"id":"2407.12332","title":"Why Do You Grok? A Theoretical Analysis of Grokking Modular Addition","created":"2024-07-17","cited_by_count":36,"area":null},{"id":"2410.08198","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","created":"2024-10-10","cited_by_count":23,"area":null},{"id":"2410.22069","title":"Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks","created":"2024-10-29","cited_by_count":18,"area":null},{"id":"2506.01913","title":"Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2506.12543","title":"Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling","created":"2025-06-14","cited_by_count":15,"area":null},{"id":"2505.24022","title":"The Rich and the Simple: On the Implicit Bias of Adam and SGD","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2411.07724","title":"Convergence Rate Analysis of LION","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2602.16340","title":"The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2505.12387","title":"Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning","created":"2025-05-18","cited_by_count":9,"area":null},{"id":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2509.26337","title":"FedMuon: Federated Learning with Bias-corrected LMO-based Optimization","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2502.02132","title":"How Memory in Optimization Algorithms Implicitly Modifies the Loss","created":"2025-02-04","cited_by_count":6,"area":null},{"id":"2511.20584","title":"A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent","created":"2025-11-25","cited_by_count":5,"area":null},{"id":"2512.00763","title":"Provable Benefit of SignGD: A Minimal Model Under Heavy-Tailed Class Imbalance","created":"2025-11-30","cited_by_count":5,"area":null},{"id":"2411.05746","title":"Continuous-Time Analysis of Adaptive Optimization and Normalization","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2505.15222","title":"Continuous Representation Methods, Theories, and Applications: An Overview and Perspectives","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2511.22270","title":"Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2605.06152","title":"Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2410.14158","title":"A Mirror Descent Perspective of Smoothed Sign Descent","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2602.01105","title":"OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\\ell_{\\infty}$ Implicit Biases","created":"2026-02-01","cited_by_count":3,"area":null},{"id":"2605.11172","title":"Optimistic Dual Averaging Unifies Modern Optimizers","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.19458","title":"Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2502.11893","title":"Rethinking Benign Overfitting in Two-Layer Neural Networks","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2510.26303","title":"Implicit Bias of Per-sample Adam on Separable Data: Departure from the Full-batch Regime","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2605.18528","title":"Tight Complexity of Muon under Heavy-Tailed Noise","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2410.11551","title":"LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2412.07971","title":"Effectiveness of Distributed Gradient Descent with Local Steps for Overparameterized Models","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2601.07326","title":"Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2602.19945","title":"DP-FedAdamW: An Efficient Optimizer for Differentially Private Federated Large Models","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.02649","title":"HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.18845","title":"First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2608.19762","title":"Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2504.08628","title":"Gradient Descent Robustly Learns the Intrinsic Dimension of Data in Training Convolutional Neural Networks","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2603.10485","title":"Dual Space Preconditioning for Gradient Descent in the Overparameterized Regime","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2605.05577","title":"Accelerating LMO-Based Optimization via Implicit Gradient Transport","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.09991","title":"Optimizer-Induced Mode Connectivity: From AdamW to Muon","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.16720","title":"Effects of width-dependent model hyperparameters and $\\ell_2$-regularization on the loss landscape of two-layer ReLU networks","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.04382","title":"Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05136","title":"The Loss Does Not See the Basis, but Adam Does","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.14803","title":"Is Grokking a Loss of Normal Hyperbolicity of the Interpolation Manifold?","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.33152","title":"Convergence of Practical Muon","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33904","title":"On the Two Faces of Adam in Separable Linear Classification","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.02798","title":"Muon Learns Facts Better: Understanding the Role of Spectral Orthogonalization","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}