{"total":123,"rows":[{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2103.14021","title":"Orthogonal Projection Loss","created":"2021-03-25","cited_by_count":44,"area":null},{"id":"2208.03160","title":"Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks","created":"2022-08-05","cited_by_count":39,"area":null},{"id":"2302.06594","title":"Geometric Clifford Algebra Networks","created":"2023-02-13","cited_by_count":38,"area":null},{"id":"2108.07668","title":"Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation","created":"2021-08-17","cited_by_count":35,"area":null},{"id":"2210.11620","title":"LOT: Layer-wise Orthogonal Training on Improving $\\ell_2$ Certified Robustness","created":"2022-10-20","cited_by_count":33,"area":null},{"id":"2201.04093","title":"Systematic Literature Review: Quantum Machine Learning and its applications","created":"2022-01-11","cited_by_count":32,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2202.07052","title":"Orthogonalising gradients to speed up neural network optimisation","created":"2022-02-14","cited_by_count":27,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2206.08704","title":"Maximum Class Separation as Inductive Bias in One Matrix","created":"2022-06-17","cited_by_count":21,"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":"2109.11338","title":"Orthogonal Graph Neural Networks","created":"2021-09-23","cited_by_count":19,"area":null},{"id":"2201.05120","title":"SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps","created":"2022-01-13","cited_by_count":19,"area":null},{"id":"2305.16173","title":"Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration","created":"2023-05-25","cited_by_count":19,"area":null},{"id":"2303.16510","title":"Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2108.08532","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","created":"2021-08-19","cited_by_count":17,"area":null},{"id":"2105.10827","title":"Orthogonal Ensemble Networks for Biomedical Image Segmentation","created":"2021-05-22","cited_by_count":16,"area":null},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16,"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":"2206.11225","title":"RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval","created":"2022-06-17","cited_by_count":15,"area":null},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14,"area":null},{"id":"2110.08774","title":"Nonlinear Transform Induced Tensor Nuclear Norm for Tensor Completion","created":"2021-10-17","cited_by_count":13,"area":null},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13,"area":null},{"id":"2204.11418","title":"Riemannian Hamiltonian methods for min-max optimization on manifolds","created":"2022-04-25","cited_by_count":12,"area":null},{"id":"2503.01136","title":"Prior-guided Hierarchical Harmonization Network for Efficient Image Dehazing","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2101.10143","title":"Spectral Leakage and Rethinking the Kernel Size in CNNs","created":"2021-01-25","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":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2201.12133","title":"O-ViT: Orthogonal Vision Transformer","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2210.02373","title":"Dynamical systems' based neural networks","created":"2022-10-05","cited_by_count":10,"area":null},{"id":"2303.01978","title":"Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks","created":"2023-01-26","cited_by_count":10,"area":null},{"id":"2405.16419","title":"Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers","created":"2024-05-26","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":"2302.05825","title":"Koopman-based generalization bound: New aspect for full-rank weights","created":"2023-02-12","cited_by_count":9,"area":null},{"id":"2407.20734","title":"Efficient Pareto Manifold Learning with Low-Rank Structure","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2411.00392","title":"Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization","created":"2024-11-01","cited_by_count":9,"area":null},{"id":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2105.09109","title":"An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks","created":"2021-05-19","cited_by_count":7,"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":"2302.03825","title":"Decentralized Riemannian Algorithm for Nonconvex Minimax Problems","created":"2023-02-08","cited_by_count":7,"area":null},{"id":"2409.11859","title":"Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers","created":"2024-09-18","cited_by_count":7,"area":null},{"id":"2505.12003","title":"Approximation theory for 1-Lipschitz ResNets","created":"2025-05-17","cited_by_count":7,"area":null},{"id":"2107.07110","title":"Compact and Optimal Deep Learning with Recurrent Parameter Generators","created":"2021-07-15","cited_by_count":5,"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":"2212.05599","title":"Orthogonal SVD Covariance Conditioning and Latent Disentanglement","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2301.06132","title":"Deep Diversity-Enhanced Feature Representation of Hyperspectral Images","created":"2023-01-15","cited_by_count":5,"area":null},{"id":"2303.03042","title":"Convolutional Neural Networks as 2-D systems","created":"2023-03-06","cited_by_count":5,"area":null},{"id":"2303.03611","title":"TinyAD: Memory-efficient anomaly detection for time series data in Industrial IoT","created":"2023-03-07","cited_by_count":5,"area":null},{"id":"2306.03228","title":"Discovering Novel Biological Traits From Images Using Phylogeny-Guided Neural Networks","created":"2023-06-05","cited_by_count":5,"area":null},{"id":"2403.13351","title":"OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2104.00219","title":"Fast Jacobian-Vector Product for Deep Networks","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2207.02119","title":"Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2209.04293","title":"Robust-by-Design Classification via Unitary-Gradient Neural Networks","created":"2022-09-09","cited_by_count":4,"area":null},{"id":"2302.14277","title":"DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features","created":"2023-02-28","cited_by_count":4,"area":null},{"id":"2303.05066","title":"Distortion-Disentangled Contrastive Learning","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2310.16647","title":"Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2402.00240","title":"Spectral Norm of Convolutional Layers with Circular and Zero Paddings","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2406.02225","title":"Riemannian coordinate descent algorithms on matrix manifolds","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2406.19301","title":"MCNC: Manifold-Constrained Reparameterization for Neural Compression","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2407.02811","title":"SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2510.13451","title":"Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts","created":"2025-10-15","cited_by_count":4,"area":"safety"},{"id":"2601.08100","title":"Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2110.00684","title":"Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2110.11400","title":"Channel redundancy and overlap in convolutional neural networks with channel-wise NNK graphs","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2210.12818","title":"Pushing the Efficiency Limit Using Structured Sparse Convolutions","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2301.05440","title":"Learnable Heterogeneous Convolution: Learning both topology and strength","created":"2023-01-13","cited_by_count":3,"area":null},{"id":"2302.11446","title":"Singular value decomposition based matrix surgery","created":"2023-02-22","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":"2308.01547","title":"Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2402.00653","title":"Coherent Feed Forward Quantum Neural Network","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2406.01755","title":"Sparser, Better, Deeper, Stronger: Improving Sparse Training with Exact Orthogonal Initialization","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2505.12378","title":"Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2505.21626","title":"Learning where to learn: Training data distribution optimization for scientific machine learning","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2602.14656","title":"An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale","created":"2026-02-16","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":"2205.10089","title":"Kernel Normalized Convolutional Networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2206.10562","title":"Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth","created":"2022-06-21","cited_by_count":2,"area":null},{"id":"2206.13130","title":"Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search","created":"2022-06-27","cited_by_count":2,"area":"distill"},{"id":"2306.10001","title":"Group Orthogonalization Regularization For Vision Models Adaptation and Robustness","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2407.01331","title":"Restyling Unsupervised Concept Based Interpretable Networks with Generative Models","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2501.15828","title":"Hybrid Quantum Neural Networks with Amplitude Encoding: Advancing Recovery Rate Predictions","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2501.18164","title":"Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2504.18103","title":"Bayesian Quantum Orthogonal Neural Networks for Anomaly Detection","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2506.04487","title":"OrthoGrad Improves Neural Calibration","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2509.23373","title":"Graph Your Own Prompt","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.21468","title":"Finite-Time Analysis of Stochastic Nonconvex Nonsmooth Optimization on the Riemannian Manifolds","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2207.10049","title":"Pretraining a Neural Network before Knowing Its Architecture","created":"2022-07-20","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":"2407.17738","title":"Enhancing Fine-grained Object Detection in Aerial Images via Orthogonal Mapping","created":"2024-07-25","cited_by_count":1,"area":null},{"id":"2501.18895","title":"Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2505.04888","title":"Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection","created":"2025-05-08","cited_by_count":1,"area":null},{"id":"2602.07579","title":"Enhancing Time Series Classification with Diversity-Driven Neural Network Ensembles","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.21684","title":"LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation","created":"2026-03-23","cited_by_count":1,"area":null}],"next_cursor":"100"}