{"total":34,"rows":[{"id":"2405.19454","title":"Deep Grokking: Would Deep Neural Networks Generalize Better?","created":"2024-05-29","cited_by_count":15,"area":null},{"id":"2410.04489","title":"Grokking at the Edge of Linear Separability","created":"2024-10-06","cited_by_count":12,"area":null},{"id":"2408.06663","title":"Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2501.10077","title":"Double descent in quantum kernel methods","created":"2025-01-17","cited_by_count":9,"area":null},{"id":"2404.07815","title":"Post-Hoc Reversal: Are We Selecting Models Prematurely?","created":"2024-04-11","cited_by_count":8,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2506.11135","title":"Large Language Models and Emergence: A Complex Systems Perspective","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2403.20200","title":"High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile","created":"2024-03-29","cited_by_count":5,"area":null},{"id":"2404.02973","title":"Scaling Laws for Galaxy Images","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2407.08641","title":"How more data can hurt: Instability and regularization in next-generation reservoir computing","created":"2024-07-11","cited_by_count":5,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2502.18339","title":"Correlating and Predicting Human Evaluations of Language Models from Natural Language Processing Benchmarks","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2503.21419","title":"Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2406.04146","title":"Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2410.16546","title":"Transformers as Implicit State Estimators: In-Context Learning in Dynamical Systems","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2505.01751","title":"A dynamic view of some anomalous phenomena in SGD","created":"2025-05-03","cited_by_count":2,"area":null},{"id":"2505.10466","title":"FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","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":"2511.04514","title":"Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.22757","title":"Unveiling Scaling Behaviors in Molecular Language Models: Effects of Model Size, Data, and Representation","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2312.03951","title":"Understanding the Role of Optimization in Double Descent","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2408.08294","title":"eGAD! double descent is explained by Generalized Aliasing Decomposition","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2409.14123","title":"Consistency for Large Neural Networks: Regression and Classification","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2503.02129","title":"Path Regularization: A Near-Complete and Optimal Nonasymptotic Generalization Theory for Multilayer Neural Networks and Double Descent Phenomenon","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.17254","title":"Approach to Finding a Robust Deep Learning Model","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2509.25216","title":"Evaluating Double Descent in Machine Learning: Insights from Tree-Based Models Applied to a Genomic Prediction Task","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2511.17825","title":"Analog Physical Systems Can Exhibit Double Descent","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.14880","title":"Task Matrices: Linear Maps for Cross-Model Finetuning Transfer","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2602.12680","title":"A Regularization-Sharpness Tradeoff for Linear Interpolators","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.09243","title":"How Much is Brain Data Worth for Machine Learning?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2610.04507","title":"LoRA's Second Descent Extends Beyond Parameter Parity","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}