{"total":17,"rows":[{"id":"2410.23819","title":"Weight decay induces low-rank attention layers","created":"2024-10-31","cited_by_count":27,"area":null},{"id":"2309.16932","title":"Symmetry Induces Structure and Constraint of Learning","created":"2023-09-29","cited_by_count":25,"area":null},{"id":"2502.02496","title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries","created":"2025-02-04","cited_by_count":14,"area":null},{"id":"2306.05857","title":"How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective","created":"2023-06-09","cited_by_count":9,"area":null},{"id":"2303.13093","title":"Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent","created":"2023-03-23","cited_by_count":8,"area":null},{"id":"2408.15495","title":"Remove Symmetries to Control Model Expressivity and Improve Optimization","created":"2024-08-28","cited_by_count":8,"area":null},{"id":"2603.02064","title":"Never Saddle for Reparameterized Steepest Descent as Mirror Flow","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2509.23898","title":"Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2311.03096","title":"Weight-Sharing Regularization","created":"2023-11-06","cited_by_count":2,"area":null},{"id":"2502.00744","title":"CoNNect: Connectivity-Based Regularization for Structural Pruning","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2505.21791","title":"Global Minimizers of $\\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2602.19782","title":"Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2604.18857","title":"Task Switching Without Forgetting via Proximal Decoupling","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.21104","title":"HORST: Composing Optimizer Geometries for Sparse Transformer Training","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.25134","title":"Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2609.23995","title":"Simpler Methods Work Better for L1 Penalized Logistic Models and Large Datasets","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.06120","title":"Mind the Drift: Diagonal Linear Networks Under Large Learning Rates","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}