{"total":73,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"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":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2107.06608","title":"Continuous vs. Discrete Optimization of Deep Neural Networks","created":"2021-07-14","cited_by_count":34,"area":null},{"id":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","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":"2412.07224","title":"Parseval Regularization for Continual Reinforcement Learning","created":"2024-12-10","cited_by_count":21,"area":"deeprl"},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2206.01103","title":"Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images","created":"2022-06-02","cited_by_count":17,"area":null},{"id":"2503.04877","title":"Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning","created":"2025-03-06","cited_by_count":17,"area":"offlinerl"},{"id":"2210.05247","title":"Training Debiased Subnetworks with Contrastive Weight Pruning","created":"2022-10-11","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":"2312.09257","title":"Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment","created":"2023-12-01","cited_by_count":15,"area":null},{"id":"2312.02829","title":"MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition","created":"2023-12-05","cited_by_count":14,"area":"mechinterp"},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2105.05553","title":"Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks","created":"2021-05-12","cited_by_count":10,"area":null},{"id":"2310.07235","title":"Are GATs Out of Balance?","created":"2023-10-11","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":"2207.09432","title":"Deep equilibrium networks are sensitive to initialization statistics","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2209.09315","title":"Deep Linear Networks can Benignly Overfit when Shallow Ones Do","created":"2022-09-19","cited_by_count":8,"area":null},{"id":"2110.11886","title":"Conditionally Gaussian PAC-Bayes","created":"2021-10-22","cited_by_count":7,"area":null},{"id":"2207.08148","title":"Improving Deep Neural Network Random Initialization Through Neuronal Rewiring","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2311.03733","title":"Improved weight initialization for deep and narrow feedforward neural network","created":"2023-11-07","cited_by_count":7,"area":null},{"id":"2206.10581","title":"Nimble GNN Embedding with Tensor-Train Decomposition","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2108.00051","title":"Coordinate descent on the orthogonal group for recurrent neural network training","created":"2021-07-30","cited_by_count":5,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2209.13394","title":"Magnitude and Angle Dynamics in Training Single ReLU Neurons","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2411.02139","title":"Theoretical characterisation of the Gauss-Newton conditioning in Neural Networks","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2505.20137","title":"ePC: Fast and Deep Predictive Coding in Digital Simulation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2104.05878","title":"On the validity of kernel approximations for orthogonally-initialized neural networks","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2201.04543","title":"Eigenvalue Distribution of Large Random Matrices Arising in Deep Neural Networks: Orthogonal Case","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2204.08306","title":"A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks","created":"2022-04-18","cited_by_count":4,"area":null},{"id":"2606.05414","title":"When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories","created":"2026-06-03","cited_by_count":4,"area":"agents"},{"id":"2102.12307","title":"Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments","created":"2021-02-24","cited_by_count":3,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2302.01002","title":"Over-parameterised Shallow Neural Networks with Asymmetrical Node Scaling: Global Convergence Guarantees and Feature Learning","created":"2023-02-02","cited_by_count":3,"area":null},{"id":"2302.08733","title":"Data Driven Reward Initialization for Preference based Reinforcement Learning","created":"2023-02-17","cited_by_count":3,"area":"alignment"},{"id":"2309.00296","title":"End-to-end Lidar-Driven Reinforcement Learning for Autonomous Racing","created":"2023-09-01","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":"2410.09640","title":"Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2605.12580","title":"CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2105.08911","title":"Multi-layer Perceptron Trainability Explained via Variability","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2402.02454","title":"On the Role of Initialization on the Implicit Bias in Deep Linear Networks","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2405.01606","title":"Enhancing the Trainability of Variational Quantum Circuits with Regularization Strategies","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2405.13901","title":"Discrete Cosine Transform Based Decorrelated Attention for Vision Transformers","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2505.03561","title":"Ergodic Generative Flows","created":"2025-05-06","cited_by_count":2,"area":"diffusion"},{"id":"2204.05477","title":"Deep Normed Embeddings for Patient Representation","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2302.04729","title":"Constrained Empirical Risk Minimization: Theory and Practice","created":"2023-02-09","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":"2502.11152","title":"Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks","created":"2025-02-16","cited_by_count":1,"area":null},{"id":"2510.22652","title":"If You Want to Be Robust, Be Wary of Initialization","created":"2025-10-26","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":"2106.12562","title":"Feature Alignment as a Generative Process","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2201.02761","title":"Global Convergence Analysis of Deep Linear Networks with A One-neuron Layer","created":"2022-01-08","cited_by_count":0,"area":null},{"id":"2206.03254","title":"Demystifying the Global Convergence Puzzle of Learning Over-parameterized ReLU Nets in Very High Dimensions","created":"2022-06-05","cited_by_count":0,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2211.13902","title":"TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2301.12193","title":"CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning","created":"2023-01-28","cited_by_count":0,"area":null},{"id":"2304.03374","title":"Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2405.01067","title":"AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2508.18960","title":"Enhancing compact convolutional transformers with super attention","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.00362","title":"Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2509.26294","title":"Noise-Guided Transport for Imitation Learning","created":"2025-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2601.21581","title":"Evaluating Prediction Uncertainty Estimates from BatchEnsemble","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2601.23148","title":"Compressed BC-LISTA via Low-Rank Convolutional Decomposition","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.01308","title":"Dispelling the Curse of Singularities in Neural Network Optimizations","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2602.10949","title":"Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.28040","title":"Bit-Identical Medical Deep Learning via Structured Orthogonal Initialization","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2605.19781","title":"From SGD to Muon: Adaptive Optimization via Schatten-p Norms","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.26012","title":"Learning in Low-Dimensional Subspaces: Orthogonal Bottlenecks for Reinforcement Learning","created":"2026-05-25","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}