{"total":32,"rows":[{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2108.01538","title":"Geometry of Linear Convolutional Networks","created":"2021-08-03","cited_by_count":27,"area":null},{"id":"2107.13289","title":"The loss landscape of deep linear neural networks: a second-order analysis","created":"2021-07-28","cited_by_count":24,"area":null},{"id":"2108.02040","title":"Convergence of gradient descent for learning linear neural networks","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2209.04036","title":"Functional dimension of feedforward ReLU neural networks","created":"2022-09-08","cited_by_count":21,"area":null},{"id":"2402.00949","title":"Geometry of Polynomial Neural Networks","created":"2024-02-01","cited_by_count":21,"area":null},{"id":"2501.18915","title":"Algebra Unveils Deep Learning -- An Invitation to Neuroalgebraic Geometry","created":"2025-01-31","cited_by_count":21,"area":null},{"id":"2304.05752","title":"Function Space and Critical Points of Linear Convolutional Networks","created":"2023-04-12","cited_by_count":19,"area":null},{"id":"2408.17221","title":"Geometry of Lightning Self-Attention: Identifiability and Dimension","created":"2024-08-30","cited_by_count":16,"area":null},{"id":"2408.04569","title":"Activation degree thresholds and expressiveness of polynomial neural networks","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2401.16613","title":"Algebraic Complexity and Neurovariety of Linear Convolutional Networks","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2110.07409","title":"The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs","created":"2021-10-14","cited_by_count":9,"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":"2303.03027","title":"Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss","created":"2023-03-06","cited_by_count":7,"area":null},{"id":"2601.21645","title":"Identifiable Equivariant Networks are Layerwise Equivariant","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2511.19703","title":"The Alexander-Hirschowitz theorem for neurovarieties","created":"2025-11-24","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":"2309.13736","title":"Geometry of Linear Neural Networks: Equivariance and Invariance under Permutation Groups","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2309.10370","title":"Geometric structure of shallow neural networks and constructive ${\\mathcal L}^2$ cost minimization","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2506.13714","title":"Understanding Learning Invariance in Deep Linear Networks","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2408.01517","title":"Gradient flow in parameter space is equivalent to linear interpolation in output space","created":"2024-08-02","cited_by_count":2,"area":null},{"id":"2506.20344","title":"A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2603.29566","title":"The Geometry of Polynomial Group Convolutional Neural Networks","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2512.21029","title":"Critical Points of Degenerate Metrics on Algebraic Varieties: A Tale of Overparametrization","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2604.15632","title":"Algebraic Invariants of Lightning Self-Attention","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2505.24668","title":"Impact of Bottleneck Layers and Skip Connections on the Generalization of Linear Denoising Autoencoders","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.19747","title":"TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations","created":"2025-07-26","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":"2608.06597","title":"Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.27113","title":"Linear Independence of Polynomial Compositions and Identifiability of Deep Neural Networks","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.13057","title":"Benign Loss Landscapes Can Coexist with Worst-Case Hardness","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.34549","title":"On Parameter Symmetries and Conservation Laws in Gradient Flow","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}