{"total":82,"rows":[{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2110.04840","title":"Heavy Ball Neural Ordinary Differential Equations","created":"2021-10-10","cited_by_count":42,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35,"area":null},{"id":"2311.11108","title":"Auxiliary Losses for Learning Generalizable Concept-based Models","created":"2023-11-18","cited_by_count":35,"area":null},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2101.02486","title":"Deep Learning Methods for Vessel Trajectory Prediction based on Recurrent Neural Networks","created":"2021-01-07","cited_by_count":32,"area":null},{"id":"2405.21064","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","created":"2024-05-31","cited_by_count":25,"area":null},{"id":"2302.08210","title":"A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold","created":"2023-02-16","cited_by_count":21,"area":null},{"id":"2105.04854","title":"Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity","created":"2021-05-11","cited_by_count":20,"area":null},{"id":"2112.03328","title":"Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-12-06","cited_by_count":20,"area":null},{"id":"2109.11338","title":"Orthogonal Graph Neural Networks","created":"2021-09-23","cited_by_count":19,"area":null},{"id":"2105.13205","title":"Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Design","created":"2021-05-27","cited_by_count":18,"area":null},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2112.09046","title":"Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approach","created":"2021-12-16","cited_by_count":12,"area":null},{"id":"2112.14949","title":"Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2205.14173","title":"Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2406.10019","title":"Group and Shuffle: Efficient Structured Orthogonal Parametrization","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2510.08177","title":"Long-tailed Recognition with Model Rebalancing","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2101.09346","title":"On the Local Linear Rate of Consensus on the Stiefel Manifold","created":"2021-01-22","cited_by_count":8,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2106.09121","title":"Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2308.10547","title":"Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold","created":"2023-08-21","cited_by_count":7,"area":null},{"id":"2405.08540","title":"Generalizing Knowledge Graph Embedding with Universal Orthogonal Parameterization","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2112.08950","title":"Stable Long-Term Recurrent Video Super-Resolution","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2308.12585","title":"Persistent learning signals and working memory without continuous attractors","created":"2023-08-24","cited_by_count":6,"area":null},{"id":"2506.15507","title":"Over-squashing in Spatiotemporal Graph Neural Networks","created":"2025-06-18","cited_by_count":6,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2210.01245","title":"Random orthogonal additive filters: a solution to the vanishing/exploding gradient of deep neural networks","created":"2022-10-03","cited_by_count":5,"area":null},{"id":"2212.00228","title":"Gated Recurrent Neural Networks with Weighted Time-Delay Feedback","created":"2022-12-01","cited_by_count":5,"area":null},{"id":"2303.06972","title":"Leveraging Neural Koopman Operators to Learn Continuous Representations of Dynamical Systems from Scarce Data","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2606.06479","title":"Pretraining Recurrent Networks without Recurrence","created":"2026-06-04","cited_by_count":5,"area":null},{"id":"2106.10704","title":"Better Training using Weight-Constrained Stochastic Dynamics","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2208.06496","title":"Orthogonal Gated Recurrent Unit with Neumann-Cayley Transformation","created":"2022-08-12","cited_by_count":4,"area":null},{"id":"2102.09589","title":"A Differential Geometry Perspective on Orthogonal Recurrent Models","created":"2021-02-18","cited_by_count":3,"area":null},{"id":"2103.06583","title":"Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2111.03628","title":"Exploiting a Zoo of Checkpoints for Unseen Tasks","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2201.11016","title":"Recency Dropout for Recurrent Recommender Systems","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2204.04876","title":"Lyapunov-Guided Representation of Recurrent Neural Network Performance","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2302.10144","title":"Stabilising and accelerating light gated recurrent units for automatic speech recognition","created":"2023-02-16","cited_by_count":3,"area":null},{"id":"2306.09939","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2306.14753","title":"The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2102.11855","title":"Deep Unitary Convolutional Neural Networks","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2208.13643","title":"A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2302.07396","title":"Convolutional unitary or orthogonal recurrent neural networks","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2307.14823","title":"Fading memory as inductive bias in residual recurrent networks","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2508.12121","title":"Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks","created":"2025-08-16","cited_by_count":2,"area":null},{"id":"2602.22255","title":"Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2211.08408","title":"On the biological plausibility of orthogonal initialisation for solving gradient instability in deep neural networks","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2212.07547","title":"Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","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":"2402.04012","title":"Quantized Approximately Orthogonal Recurrent Neural Networks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2405.13854","title":"On the dynamics of convolutional recurrent neural networks near their critical point","created":"2024-05-22","cited_by_count":1,"area":null},{"id":"2408.08408","title":"Oja's plasticity rule overcomes several challenges of training neural networks under biological constraints","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2410.03977","title":"Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification","created":"2024-10-04","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":"2506.07351","title":"Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2506.19022","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2605.11855","title":"Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2609.02672","title":"oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2106.04088","title":"A Lightweight and Gradient-Stable Neural Layer","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2109.01731","title":"Acceleration Method for Learning Fine-Layered Optical Neural Networks","created":"2021-09-01","cited_by_count":0,"area":null},{"id":"2210.01348","title":"Fast Saturating Gate for Learning Long Time Scales with Recurrent Neural Networks","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2401.01023","title":"CautionSuicide: A Deep Learning Based Approach for Detecting Suicidal Ideation in Real Time Chatbot Conversation","created":"2024-01-02","cited_by_count":0,"area":null},{"id":"2403.15832","title":"Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2502.00047","title":"HadamRNN: Binary and Sparse Ternary Orthogonal RNNs","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2504.08964","title":"Bidirectional Linear Recurrent Models for Sequence-Level Multisource Fusion","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2504.13531","title":"Can Local Representation Alignment RNNs Solve Temporal Tasks?","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2506.01350","title":"Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2507.22045","title":"Weight-Parameterization in Continuous Time Deep Neural Networks for Surrogate Modeling","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2603.25779","title":"Pure and physics-guided deep learning approaches for spatio-temporal groundwater level prediction","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.06729","title":"The E$\\Delta$-MHC-Geo Transformer: Adaptive Geodesic Operations with Guaranteed Orthogonality","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.15085","title":"An Integrable Token Mixing Layer from the Generalized Yang Baxter Equation","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2607.04535","title":"ManifoldFlow: Spectrum-Learnable Stiefel Optimization via SPD Relaxation","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2610.14030","title":"Rotate the Loop: Blockwise Conformality for Looped Transformers","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}