{"total":44,"rows":[{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146,"area":null},{"id":"2103.10948","title":"The Shape of Learning Curves: a Review","created":"2021-03-19","cited_by_count":70,"area":null},{"id":"2111.03947","title":"Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning","created":"2021-11-06","cited_by_count":43,"area":null},{"id":"2210.04860","title":"Second-order regression models exhibit progressive sharpening to the edge of stability","created":"2022-10-10","cited_by_count":40,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2303.14151","title":"Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle","created":"2023-03-24","cited_by_count":37,"area":null},{"id":"2306.13253","title":"Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok","created":"2023-06-23","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":"2106.03212","title":"Towards an Understanding of Benign Overfitting in Neural Networks","created":"2021-06-06","cited_by_count":30,"area":null},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"area":null},{"id":"2106.02261","title":"Out-of-Distribution Generalization in Kernel Regression","created":"2021-06-04","cited_by_count":21,"area":null},{"id":"2201.13383","title":"Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2212.13069","title":"Homophily modulates double descent generalization in graph convolution networks","created":"2022-12-26","cited_by_count":13,"area":null},{"id":"2210.12082","title":"A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models","created":"2022-10-21","cited_by_count":11,"area":null},{"id":"2205.12937","title":"Mitigating multiple descents: A model-agnostic framework for risk monotonization","created":"2022-05-25","cited_by_count":10,"area":null},{"id":"2208.09897","title":"Multiple Descent in the Multiple Random Feature Model","created":"2022-08-21","cited_by_count":10,"area":null},{"id":"2208.03848","title":"Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality","created":"2022-08-08","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":"2110.09502","title":"Minimum $\\ell_{1}$-norm interpolators: Precise asymptotics and multiple descent","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2110.06910","title":"On the Double Descent of Random Features Models Trained with SGD","created":"2021-10-13","cited_by_count":5,"area":null},{"id":"2212.06757","title":"Gradient flow in the gaussian covariate model: exact solution of learning curves and multiple descent structures","created":"2022-12-13","cited_by_count":5,"area":null},{"id":"2311.07013","title":"A PAC-Bayesian Perspective on the Interpolating Information Criterion","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2406.11703","title":"Unveiling Multiple Descents in Unsupervised Autoencoders","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2202.09885","title":"On Optimal Early Stopping: Over-informative versus Under-informative Parametrization","created":"2022-02-20","cited_by_count":4,"area":null},{"id":"2302.13511","title":"Extrapolated cross-validation for randomized ensembles","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2303.04833","title":"Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning","created":"2023-02-24","cited_by_count":4,"area":null},{"id":"2305.14689","title":"Least Squares Regression Can Exhibit Under-Parameterized Double Descent","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2107.00797","title":"Mitigating deep double descent by concatenating inputs","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2403.10459","title":"Understanding the Double Descent Phenomenon in Deep Learning","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2203.03110","title":"Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning","created":"2022-03-07","cited_by_count":2,"area":null},{"id":"2305.16179","title":"Dropout Drops Double Descent","created":"2023-05-25","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":"2202.11817","title":"Benefit of Interpolation in Nearest Neighbor Algorithms","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2307.02454","title":"Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2201.11939","title":"With Greater Distance Comes Worse Performance: On the Perspective of Layer Utilization and Model Generalization","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2206.03213","title":"Improving Students' Academic Performance with AI and Semantic Technologies","created":"2022-05-02","cited_by_count":0,"area":null},{"id":"2212.00433","title":"Regularization Trade-offs with Fake Features","created":"2022-12-01","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":"2410.00699","title":"Investigating the Impact of Model Complexity in Large Language Models","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2601.08316","title":"Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting","created":"2026-01-13","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":"2606.31110","title":"Explaining Machine Learning and Memorization with Statistical Mechanics","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}