{"total":192,"rows":[{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2106.09352","title":"Large Scale Private Learning via Low-rank Reparametrization","created":"2021-06-17","cited_by_count":88,"area":null},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2112.15383","title":"Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs","created":"2021-12-31","cited_by_count":53,"area":null},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52,"area":null},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43,"area":null},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41,"area":null},{"id":"2106.03812","title":"Neural Monge Map estimation and its applications","created":"2021-06-07","cited_by_count":40,"area":null},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"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":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","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":"2106.04110","title":"A self consistent theory of Gaussian Processes captures feature learning effects in finite CNNs","created":"2021-06-08","cited_by_count":33,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2211.06506","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","created":"2022-11-11","cited_by_count":30,"area":null},{"id":"2108.00781","title":"Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers","created":"2021-08-02","cited_by_count":27,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2203.14661","title":"Random matrix analysis of deep neural network weight matrices","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","cited_by_count":21,"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":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2509.24882","title":"Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime","created":"2025-09-29","cited_by_count":20,"area":null},{"id":"2106.00734","title":"Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics","created":"2021-06-01","cited_by_count":19,"area":null},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2110.03501","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","created":"2021-10-07","cited_by_count":17,"area":null},{"id":"2106.03696","title":"Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2410.18938","title":"A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities","created":"2024-10-24","cited_by_count":16,"area":null},{"id":"2305.18383","title":"A Three-regime Model of Network Pruning","created":"2023-05-28","cited_by_count":15,"area":null},{"id":"2503.23616","title":"Interpretable Machine Learning in Physics: A Review","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2210.06771","title":"Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning","created":"2022-10-13","cited_by_count":13,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2402.13999","title":"Asymptotics of Learning with Deep Structured (Random) Features","created":"2024-02-21","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":"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":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2308.11567","title":"Low Tensor Rank Learning of Neural Dynamics","created":"2023-08-22","cited_by_count":12,"area":null},{"id":"2405.13975","title":"HOPE for a Robust Parameterization of Long-memory State Space Models","created":"2024-05-22","cited_by_count":12,"area":null},{"id":"2505.23811","title":"LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2603.10067","title":"HTMuon: Improving Muon via Heavy-Tailed Spectral Correction","created":"2026-03-10","cited_by_count":12,"area":null},{"id":"2406.11151","title":"Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2104.12416","title":"Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression","created":"2021-04-26","cited_by_count":10,"area":null},{"id":"2506.03470","title":"Models of Heavy-Tailed Mechanistic Universality","created":"2025-06-04","cited_by_count":10,"area":null},{"id":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2509.15735","title":"EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs","created":"2025-09-19","cited_by_count":10,"area":null},{"id":"2206.03927","title":"Boundary between noise and information applied to filtering neural network weight matrices","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2303.05369","title":"Data-dependent Generalization Bounds via Variable-Size Compressibility","created":"2023-03-09","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2406.04657","title":"From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks","created":"2024-06-07","cited_by_count":9,"area":null},{"id":"2507.12709","title":"From SGD to Spectra: A Theory of Neural Network Weight Dynamics","created":"2025-07-17","cited_by_count":9,"area":null},{"id":"2510.03358","title":"Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2602.05846","title":"Optimal scaling laws in learning hierarchical multi-index models","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2208.06894","title":"The SVD of Convolutional Weights: A CNN Interpretability Framework","created":"2022-08-14","cited_by_count":8,"area":null},{"id":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2512.14366","title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2110.01899","title":"Random matrices in service of ML footprint: ternary random features with no performance loss","created":"2021-10-05","cited_by_count":7,"area":null},{"id":"2206.09901","title":"Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime","created":"2022-06-20","cited_by_count":7,"area":null},{"id":"2303.17940","title":"Per-Example Gradient Regularization Improves Learning Signals from Noisy Data","created":"2023-03-31","cited_by_count":7,"area":null},{"id":"2304.02911","title":"Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2310.12802","title":"An effective theory of collective deep learning","created":"2023-10-19","cited_by_count":7,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2310.13033","title":"LASER: Linear Compression in Wireless Distributed Optimization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2501.06386","title":"Using Pre-trained LLMs for Multivariate Time Series Forecasting","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2509.24914","title":"Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2603.15678","title":"Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales","created":"2026-03-14","cited_by_count":6,"area":null},{"id":"2305.01143","title":"Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective","created":"2023-05-02","cited_by_count":5,"area":null},{"id":"2310.03165","title":"Enhancing Accuracy in Deep Learning Using Random Matrix Theory","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2510.02676","title":"To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration","created":"2025-10-03","cited_by_count":5,"area":null},{"id":"2605.05683","title":"Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2111.13786","title":"Learning from learning machines: a new generation of AI technology to meet the needs of science","created":"2021-11-27","cited_by_count":4,"area":null},{"id":"2201.04543","title":"Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Case","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2405.15706","title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2407.13841","title":"Many Perception Tasks are Highly Redundant Functions of their Input Data","created":"2024-07-18","cited_by_count":4,"area":null},{"id":"2410.14602","title":"Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2502.06820","title":"LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2601.22137","title":"PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2406.16988","title":"MD tree: a model-diagnostic tree grown on loss landscape","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2411.09807","title":"Evaluating Loss Landscapes from a Topology Perspective","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2502.18428","title":"Global law of conjugate kernel random matrices with heavy-tailed weights","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2602.02195","title":"State Rank Dynamics in Linear Attention LLMs","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.24746","title":"Grokking as a Falsifiable Finite-Size Transition","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2604.18450","title":"Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2605.28819","title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2103.07986","title":"Pre-interpolation loss behaviour in neural networks","created":"2021-03-14","cited_by_count":2,"area":null},{"id":"2108.09507","title":"Shift-Curvature, SGD, and Generalization","created":"2021-08-21","cited_by_count":2,"area":null},{"id":"2204.02485","title":"Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization","created":"2022-04-05","cited_by_count":2,"area":null},{"id":"2303.08986","title":"Deep Learning Weight Pruning with RMT-SVD: Increasing Accuracy and Reducing Overfitting","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2409.04494","title":"Diff-INR: Generative Regularization for Electrical Impedance Tomography","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2410.17998","title":"Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2411.12136","title":"Visualizing Loss Functions as Topological Landscape Profiles","created":"2024-11-19","cited_by_count":2,"area":null}],"next_cursor":"100"}