{"total":83,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116,"area":null},{"id":"2406.08466","title":"Scaling Laws in Linear Regression: Compute, Parameters, and Data","created":"2024-06-12","cited_by_count":57,"area":null},{"id":"2409.17858","title":"How Feature Learning Can Improve Neural Scaling Laws","created":"2024-09-26","cited_by_count":56,"area":null},{"id":"2405.00592","title":"Scaling and renormalization in high-dimensional regression","created":"2024-05-01","cited_by_count":50,"area":null},{"id":"2402.11867","title":"LoRA Training in the NTK Regime has No Spurious Local Minima","created":"2024-02-19","cited_by_count":48,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2302.00401","title":"Deterministic equivalent and error universality of deep random features learning","created":"2023-02-01","cited_by_count":35,"area":null},{"id":"2206.12543","title":"A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel","created":"2022-06-25","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":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2302.08923","title":"Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation","created":"2023-02-17","cited_by_count":26,"area":null},{"id":"2402.10127","title":"Nonlinear spiked covariance matrices and signal propagation in deep neural networks","created":"2024-02-15","cited_by_count":26,"area":null},{"id":"2206.12569","title":"Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels","created":"2022-06-25","cited_by_count":25,"area":null},{"id":"2212.12147","title":"The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes","created":"2022-12-23","cited_by_count":25,"area":null},{"id":"2405.15699","title":"Dimension-free deterministic equivalents and scaling laws for random feature regression","created":"2024-05-24","cited_by_count":23,"area":null},{"id":"2405.16747","title":"Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective","created":"2024-05-27","cited_by_count":22,"area":null},{"id":"2503.12811","title":"A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules","created":"2025-03-17","cited_by_count":22,"area":null},{"id":"2404.01233","title":"Optimal Ridge Regularization for Out-of-Distribution Prediction","created":"2024-04-01","cited_by_count":19,"area":null},{"id":"2311.14646","title":"More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory","created":"2023-11-24","cited_by_count":18,"area":null},{"id":"2303.01687","title":"Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation","created":"2023-03-03","cited_by_count":15,"area":null},{"id":"2411.12925","title":"Loss-to-Loss Prediction: Scaling Laws for All Datasets","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2503.02877","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","created":"2025-03-04","cited_by_count":15,"area":null},{"id":"2406.04606","title":"Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions","created":"2024-06-07","cited_by_count":14,"area":null},{"id":"2502.07998","title":"Adaptive kernel predictors from feature-learning infinite limits of neural networks","created":"2025-02-11","cited_by_count":13,"area":null},{"id":"2502.05075","title":"Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2206.11124","title":"A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta","created":"2022-06-22","cited_by_count":11,"area":null},{"id":"2304.13016","title":"Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation","created":"2023-04-25","cited_by_count":11,"area":null},{"id":"2310.04357","title":"Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning","created":"2023-10-06","cited_by_count":11,"area":null},{"id":"2310.18526","title":"Sample based Explanations via Generalized Representers","created":"2023-10-27","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":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2306.14975","title":"The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2410.09005","title":"Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra","created":"2024-10-11","cited_by_count":9,"area":null},{"id":"2403.07264","title":"Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2410.10075","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2505.18346","title":"On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2210.17011","title":"A picture of the space of typical learnable tasks","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2211.06077","title":"Overparameterized random feature regression with nearly orthogonal data","created":"2022-11-11","cited_by_count":7,"area":null},{"id":"2402.05674","title":"A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs","created":"2024-02-08","cited_by_count":7,"area":null},{"id":"2403.12486","title":"NTK-Guided Few-Shot Class Incremental Learning","created":"2024-03-19","cited_by_count":7,"area":null},{"id":"2409.03891","title":"Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2510.13328","title":"Thompson Sampling via Fine-Tuning of LLMs","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2306.13185","title":"An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression","created":"2023-06-22","cited_by_count":5,"area":null},{"id":"2310.01374","title":"Corrected generalized cross-validation for finite ensembles of penalized estimators","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2501.19158","title":"A theoretical framework for overfitting in energy-based modeling","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2205.08601","title":"Universal characteristics of deep neural network loss surfaces from random matrix theory","created":"2022-05-17","cited_by_count":4,"area":null},{"id":"2402.16793","title":"Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent","created":"2024-02-26","cited_by_count":4,"area":null},{"id":"2409.03734","title":"Safety vs. Performance: How Multi-Objective Learning Reduces Barriers to Market Entry","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2410.16073","title":"On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2511.07380","title":"Mining Useful General Data for Low-Resource Domain Adaptation","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2306.13255","title":"Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models","created":"2023-06-23","cited_by_count":3,"area":null},{"id":"2405.19585","title":"The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2407.17120","title":"Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2512.13491","title":"From Zipf's Law to Neural Scaling through Heaps' Law and Hilberg's Hypothesis","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2602.17385","title":"Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2605.09552","title":"Phases of Muon: When Muon Eclipses SignSGD","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2308.00556","title":"Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2402.15441","title":"Active Few-Shot Fine-Tuning","created":"2024-02-13","cited_by_count":2,"area":null},{"id":"2410.04228","title":"SGD with memory: fundamental properties and stochastic acceleration","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2410.13991","title":"Generalization for Least Squares Regression With Simple Spiked Covariances","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2506.12454","title":"On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classification","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.06961","title":"The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2311.14120","title":"Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2403.11696","title":"Generalization error of spectral algorithms","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2408.15784","title":"Implicit Regularization Paths of Weighted Neural Representations","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2412.05418","title":"No Free Lunch From Random Feature Ensembles: Scaling Laws and Near-Optimality Conditions","created":"2024-12-06","cited_by_count":1,"area":null},{"id":"2505.16260","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.09394","title":"A Random Matrix Theory Perspective on the Learning Dynamics of Multi-head Latent Attention","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2507.19680","title":"Feature learning is decoupled from generalization in high capacity neural networks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2509.24467","title":"Interpretable Self-Supervised Learning via Representer Landmarks and Nystr\\\"om Approximation","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2505.11006","title":"Is Supervised Learning Really That Different from Unsupervised?","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.11347","title":"Training NTK to Generalize with KARE","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2605.15240","title":"On Kernel Eigen-alignments of KRR: Reconstruction and Generalization","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2610.13123","title":"Why Heavy-Tailed Weight Spectra Predict Model Quality","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}