{"total":45,"rows":[{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533,"area":null},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427,"area":null},{"id":"2406.11011","title":"Data Shapley in One Training Run","created":"2024-06-16","cited_by_count":81,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"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":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2107.05802","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","created":"2021-07-13","cited_by_count":28,"area":null},{"id":"2312.00246","title":"Directions of Curvature as an Explanation for Loss of Plasticity","created":"2023-11-30","cited_by_count":26,"area":null},{"id":"2302.12250","title":"Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2211.13723","title":"Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective","created":"2022-11-24","cited_by_count":15,"area":null},{"id":"2110.14163","title":"Does the Data Induce Capacity Control in Deep Learning?","created":"2021-10-27","cited_by_count":14,"area":null},{"id":"2311.04163","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","created":"2023-11-07","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10,"area":null},{"id":"2602.10496","title":"Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks","created":"2026-02-11","cited_by_count":7,"area":null},{"id":"2310.17163","title":"Low-Dimensional Gradient Helps Out-of-Distribution Detection","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2606.04662","title":"Why Muon Outperforms Adam: A Curvature Perspective","created":"2026-06-03","cited_by_count":6,"area":null},{"id":"2306.04178","title":"Optimal Transport Model Distributional Robustness","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2306.07104","title":"Unveiling the Hessian's Connection to the Decision Boundary","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2410.04196","title":"Improving Generalization with Flat Hilbert Bayesian Inference","created":"2024-10-05","cited_by_count":5,"area":null},{"id":"2402.03579","title":"Deconstructing the Goldilocks Zone of Neural Network Initialization","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2110.02333","title":"On the Impact of Stable Ranks in Deep Nets","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2506.07247","title":"Promoting Ensemble Diversity with Interactive Bayesian Distributional Robustness for Fine-tuning Foundation Models","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2306.07215","title":"Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2406.07107","title":"Agnostic Sharpness-Aware Minimization","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2605.26484","title":"Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2403.13204","title":"Diversity-Aware Agnostic Ensemble of Sharpness Minimizers","created":"2024-03-19","cited_by_count":1,"area":null},{"id":"2405.12493","title":"Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2409.11995","title":"Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes","created":"2024-09-18","cited_by_count":1,"area":null},{"id":"2504.17618","title":"The effects of Hessian eigenvalue spectral density type on the applicability of Hessian analysis to generalization capability assessment of neural networks","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2606.30226","title":"Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2201.07934","title":"Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2510.04376","title":"Categorical Invariants of Learning Dynamics","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.16927","title":"Closing the Curvature Gap: Full Transformer Hessians","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2601.20172","title":"Loss Landscape Geometry of Partial Differential Equation Emulators: Or, Symmetry Learning via Gradient Alignment","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.07790","title":"Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.29983","title":"Improving Adversarial Robustness of Attribution via Implicit Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.07845","title":"Explaining Near-Zero Hessian Eigenvalues Through Approximate Symmetries in Neural Networks","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.12438","title":"Fisher Rank Inflation: A Spectral Signature of Memorization under Label Noise","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.05194","title":"Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.09919","title":"Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}