{"total":43,"rows":[{"id":"2308.12108","title":"The Local Learning Coefficient: A Singularity-Aware Complexity Measure","created":"2023-08-23","cited_by_count":51,"area":null},{"id":"2402.02364","title":"Loss Landscape Degeneracy and Stagewise Development in Transformers","created":"2024-02-04","cited_by_count":40,"area":null},{"id":"2106.16004","title":"What can linear interpolation of neural network loss landscapes tell us?","created":"2021-06-30","cited_by_count":28,"area":null},{"id":"2506.15872","title":"Hidden Breakthroughs in Language Model Training","created":"2025-06-18","cited_by_count":15,"area":null},{"id":"2501.17745","title":"Dynamics of Transient Structure in In-Context Linear Regression Transformers","created":"2025-01-29","cited_by_count":14,"area":null},{"id":"2509.26544","title":"Bayesian Influence Functions for Hessian-Free Data Attribution","created":"2025-09-30","cited_by_count":14,"area":null},{"id":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2505.11846","title":"Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2305.05089","title":"Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2402.03698","title":"Estimating the Local Learning Coefficient at Scale","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2602.00693","title":"Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities","created":"2026-01-31","cited_by_count":6,"area":null},{"id":"2106.10771","title":"Multirate Training of Neural Networks","created":"2021-06-20","cited_by_count":5,"area":null},{"id":"2303.15739","title":"Bayesian Free Energy of Deep ReLU Neural Network in Overparametrized Cases","created":"2023-03-28","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":"2507.21449","title":"From Global to Local: A Scalable Benchmark for Local Posterior Sampling","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2211.10049","title":"Recent Advances in Algebraic Geometry and Bayesian Statistics","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2307.01417","title":"Free energy of Bayesian Convolutional Neural Network with Skip Connection","created":"2023-07-04","cited_by_count":4,"area":null},{"id":"2505.02604","title":"Connecting Independently Trained Modes via Layer-Wise Connectivity","created":"2025-05-05","cited_by_count":3,"area":null},{"id":"2406.10234","title":"Review and Prospect of Algebraic Research in Equivalent Framework between Statistical Mechanics and Machine Learning Theory","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2503.22478","title":"Almost Bayesian: The Fractal Dynamics of Stochastic Gradient Descent","created":"2025-03-28","cited_by_count":2,"area":null},{"id":"2103.16080","title":"Geometry of Program Synthesis","created":"2021-03-30","cited_by_count":1,"area":null},{"id":"2302.06035","title":"Variational Bayesian Neural Networks via Resolution of Singularities","created":"2023-02-13","cited_by_count":1,"area":null},{"id":"2403.09206","title":"Upper Bound of Bayesian Generalization Error in Partial Concept Bottleneck Model (CBM): Partial CBM outperforms naive CBM","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2410.05757","title":"Temperature Optimization for Bayesian Deep Learning","created":"2024-10-08","cited_by_count":1,"area":null},{"id":"2504.11830","title":"Emergence of Computational Structure in a Neural Network Physics Simulator","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2603.29262","title":"Grokking From Abstraction to Intelligence","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.24477","title":"The Normalized Maximum Likelihood for Regular Non-Smooth Models: Measure-Theoretic Foundations and Geometric Sampling","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2306.02834","title":"Proximity to Losslessly Compressible Parameters","created":"2023-06-05","cited_by_count":0,"area":null},{"id":"2504.18017","title":"Non-identifiability distinguishes Neural Networks among Parametric Models","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2512.00686","title":"Using physics-inspired Singular Learning Theory to understand grokking & other phase transitions in modern neural networks","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2512.21447","title":"An Equivariance Toolbox for Learning Dynamics","created":"2025-12-24","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":"2603.27432","title":"The Geometric Cost of Normalization: Affine Bounds on the Bayesian Complexity of Neural Networks","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2606.22389","title":"Noise-Debiased Thermodynamic Variance for Local Learning Coefficient Probes","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.28464","title":"Singular Learning and Occam's Razor in Deep Monomial Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.23397","title":"A Statistical Difference between Single-Layer Learning and Hierarchical Learning in Wide Neural Networks","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.09840","title":"Langevin dynamics along the zero set of real-analytic potentials","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16925","title":"Wrong Operator or Blind Design? A Post-Training Diagnostic for Physics-Informed Coefficient Learning","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.20183","title":"Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.02373","title":"Percolation Dynamics in Optimization: Variance Cascades and Nested Symmetry","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.14663","title":"Symmetries and Singularities","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.00620","title":"Misalignment of Low-Loss Regions Causes Grokking","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}