{"total":46,"rows":[{"id":"2309.02390","title":"Explaining grokking through circuit efficiency","created":"2023-09-05","cited_by_count":111,"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":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94,"area":null},{"id":"2311.18817","title":"Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking","created":"2023-11-30","cited_by_count":80,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2404.04454","title":"Implicit Bias of AdamW: $\\ell_\\infty$ Norm Constrained Optimization","created":"2024-04-05","cited_by_count":58,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2207.04036","title":"Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent","created":"2022-07-08","cited_by_count":39,"area":null},{"id":"2206.12680","title":"Topology-aware Generalization of Decentralized SGD","created":"2022-06-25","cited_by_count":38,"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":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2205.12808","title":"Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","cited_by_count":23,"area":null},{"id":"2602.07852","title":"Emergent Misalignment is Easy, Narrow Misalignment is Hard","created":"2026-02-08","cited_by_count":23,"area":null},{"id":"2110.03891","title":"Does Momentum Change the Implicit Regularization on Separable Data?","created":"2021-10-08","cited_by_count":22,"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":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14,"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":"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":"2308.06703","title":"Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods","created":"2023-08-13","cited_by_count":8,"area":null},{"id":"2410.07687","title":"Learning to Compress: Local Rank and Information Compression in Deep Neural Networks","created":"2024-10-10","cited_by_count":7,"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":"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":"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":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2505.11370","title":"Understanding Nonlinear Implicit Bias via Region Counts in Input Space","created":"2025-05-16","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":"2607.06013","title":"Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2502.05668","title":"The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2108.05839","title":"Logit Attenuating Weight Normalization","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2411.06916","title":"Slowing Down Forgetting in Continual Learning","created":"2024-11-11","cited_by_count":0,"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":"2506.14806","title":"Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2508.19498","title":"UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models","created":"2025-08-27","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":"2605.19392","title":"Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37745","title":"Optimizer-dependent training dynamics converge to the same one-third optimal data scaling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04249","title":"Optimizer Geometry Sets the Pace: Spectral Learning Dynamics in Matrix Factorization","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.18294","title":"Which Optimizer Leaks Most? Optimizer Implicit Bias as a Training-Data Privacy Controller","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20112","title":"From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}