{"total":33,"rows":[{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2210.01986","title":"MAtt: A Manifold Attention Network for EEG Decoding","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2406.10685","title":"Scale Equivariant Graph Metanetworks","created":"2024-06-15","cited_by_count":24,"area":null},{"id":"2106.15739","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","created":"2021-06-29","cited_by_count":20,"area":null},{"id":"2209.03695","title":"Training Scale-Invariant Neural Networks on the Sphere Can Happen in Three Regimes","created":"2022-09-08","cited_by_count":19,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2108.01110","title":"Batch Normalization Preconditioning for Neural Network Training","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2207.07287","title":"Riemannian Natural Gradient Methods","created":"2022-07-15","cited_by_count":5,"area":null},{"id":"2404.10029","title":"Federated Learning on Riemannian Manifolds with Differential Privacy","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2101.02916","title":"Accelerating Training of Batch Normalization: A Manifold Perspective","created":"2021-01-08","cited_by_count":4,"area":null},{"id":"2110.10353","title":"Contextual Gradient Scaling for Few-Shot Learning","created":"2021-10-20","cited_by_count":4,"area":null},{"id":"2305.11417","title":"Exploring the Complexity of Deep Neural Networks through Functional Equivalence","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2101.02944","title":"BN-invariant sharpness regularizes the training model to better generalization","created":"2021-01-08","cited_by_count":3,"area":null},{"id":"2109.02345","title":"Tensor Normalization and Full Distribution Training","created":"2021-09-06","cited_by_count":3,"area":null},{"id":"2401.13708","title":"Accelerating hyperbolic t-SNE","created":"2024-01-23","cited_by_count":3,"area":null},{"id":"2304.03641","title":"A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints","created":"2023-04-07","cited_by_count":2,"area":null},{"id":"2512.13672","title":"Directional Textual Inversion for Personalized Text-to-Image Generation","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2102.03497","title":"Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization","created":"2021-02-06","cited_by_count":1,"area":null},{"id":"2110.08725","title":"A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2303.09611","title":"Decentralized Riemannian natural gradient methods with Kronecker-product approximations","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2310.12986","title":"A survey of manifold learning and its applications for multimedia","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2401.05967","title":"Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2406.02296","title":"Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2501.11584","title":"GCSAM: Gradient Centralized Sharpness Aware Minimization","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2210.06546","title":"Auto-Encoding Goodness of Fit","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2302.11076","title":"Faster Riemannian Newton-type Optimization by Subsampling and Cubic Regularization","created":"2023-02-22","cited_by_count":0,"area":null},{"id":"2306.07015","title":"Combining Primal and Dual Representations in Deep Restricted Kernel Machines Classifiers","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2401.13530","title":"Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space","created":"2024-01-24","cited_by_count":0,"area":null},{"id":"2511.07308","title":"Can Stationary Distributions of Scale-Invariant Neural Networks Be Described by the Thermodynamics of an Ideal Gas?","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2607.25299","title":"Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuning","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.09116","title":"When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.25501","title":"Continuous Optimization for p-adic Models","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}