{"total":92,"rows":[{"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":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"area":null},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78,"area":null},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2405.16002","title":"Does SGD really happen in tiny subspaces?","created":"2024-05-25","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":"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":"2312.15184","title":"ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization","created":"2023-12-23","cited_by_count":25,"area":null},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"area":null},{"id":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2309.09123","title":"Conditional Mutual Information Constrained Deep Learning for Classification","created":"2023-09-17","cited_by_count":18,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"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":"2405.15861","title":"Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","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":"2602.11948","title":"Insights on Muon from Simple Quadratics","created":"2026-02-12","cited_by_count":13,"area":null},{"id":"2111.13331","title":"Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping","created":"2021-11-26","cited_by_count":12,"area":null},{"id":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12,"area":null},{"id":"2405.00985","title":"Progressive Feedforward Collapse of ResNet Training","created":"2024-05-02","cited_by_count":12,"area":null},{"id":"2206.02927","title":"Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2410.06441","title":"Addax: Utilizing Zeroth-Order Gradients to Improve Memory Efficiency and Performance of SGD for Fine-Tuning Language Models","created":"2024-10-09","cited_by_count":11,"area":null},{"id":"2305.09088","title":"The Hessian perspective into the Nature of Convolutional Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2402.05379","title":"Trade-Offs of Diagonal Fisher Information Matrix Estimators","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2407.07810","title":"Transformer Block Coupling and its Correlation with Generalization in LLMs","created":"2024-07-10","cited_by_count":10,"area":null},{"id":"2410.10986","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2602.18584","title":"GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry","created":"2026-02-20","cited_by_count":8,"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":"2202.01944","title":"Learning Representation from Neural Fisher Kernel with Low-rank Approximation","created":"2022-02-04","cited_by_count":5,"area":null},{"id":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","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":"2505.23737","title":"On the Convergence Analysis of Muon","created":"2025-05-29","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":"2601.17261","title":"AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning","created":"2026-01-24","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":"2605.22432","title":"AMUSE: Anytime Muon with Stable Gradient Evaluation","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2208.01684","title":"Curvature-informed multi-task learning for graph networks","created":"2022-08-02","cited_by_count":3,"area":null},{"id":"2307.11948","title":"The instabilities of large learning rate training: a loss landscape view","created":"2023-07-22","cited_by_count":3,"area":null},{"id":"2410.16901","title":"Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2506.02370","title":"Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2606.19491","title":"Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2410.04264","title":"Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2501.19099","title":"Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2601.02543","title":"Normalized Conditional Mutual Information Surrogate Loss for Deep Neural Classifiers","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2111.12664","title":"MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning","created":"2021-11-24","cited_by_count":1,"area":null},{"id":"2211.04659","title":"When is Momentum Extragradient Optimal? A Polynomial-Based Analysis","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2310.04283","title":"On the Error-Propagation of Inexact Hotelling's Deflation for Principal Component Analysis","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2402.13810","title":"The Expected Loss of Preconditioned Langevin Dynamics Reveals the Hessian Rank","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2405.17277","title":"Gradients of Functions of Large Matrices","created":"2024-05-27","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":"2504.14701","title":"Connecting Parameter Magnitudes and Hessian Eigenspaces at Scale using Sketched Methods","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2602.00545","title":"Depth, Not Data: An Analysis of Hessian Spectral Bifurcation","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2602.07135","title":"Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.29466","title":"An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.10202","title":"Wolkowicz-Styan Upper Bound on the Hessian Eigenspectrum for Cross-Entropy Loss in Nonlinear Smooth Neural Networks","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2605.03373","title":"Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2607.23012","title":"Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations","created":"2026-07-25","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":"2305.18490","title":"SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2406.13879","title":"A Catalyst Framework for the Quantum Linear System Problem via the Proximal Point Algorithm","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2504.18437","title":"Enhancing Pre-Trained Model-Based Class-Incremental Learning through Neural Collapse","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2506.08428","title":"Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2602.01136","title":"A Unified Matrix-Spectral Framework for Stability and Interpretability in Deep Learning","created":"2026-02-01","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":"2605.09345","title":"Selection Plateau and a Sparsity-Dependent Hierarchy of Pruning Features","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.25674","title":"Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.31324","title":"Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.28662","title":"Closed-Form Steepest Descent Direction toward Flat Minima: Reducing Upper Bounds on the Loss Hessian Eigenspectrum in Neural Networks","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.30813","title":"Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization","created":"2026-06-29","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":"2607.18930","title":"Functional Equivalence and Geometric Diversity in Neural Network Approximations: An Empirical Characterization","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.15901","title":"Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.01034","title":"The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.14339","title":"Communication-Efficient LLM Adaptation over Decentralized GPU Meshes","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.31983","title":"Understanding the Subspace Stabilization of the Hessian and Gradient Covariance Matrix","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}