{"total":284,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256,"area":null},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158,"area":"distill"},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2106.05203","title":"EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback","created":"2021-06-09","cited_by_count":133,"area":null},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2111.00034","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","created":"2021-10-29","cited_by_count":106,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2106.15013","title":"Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction","created":"2021-06-28","cited_by_count":78,"area":null},{"id":"2112.00029","title":"Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models","created":"2021-11-30","cited_by_count":76,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2203.06311","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","created":"2022-03-12","cited_by_count":70,"area":null},{"id":"2102.11742","title":"Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed","created":"2021-02-23","cited_by_count":69,"area":null},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66,"area":"offlinerl"},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2105.01029","title":"Initialization and Regularization of Factorized Neural Layers","created":"2021-05-03","cited_by_count":58,"area":"distill"},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2105.04550","title":"Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth","created":"2021-05-10","cited_by_count":55,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52,"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":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2409.14623","title":"From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks","created":"2024-09-22","cited_by_count":49,"area":null},{"id":"2210.00226","title":"Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning","created":"2022-10-01","cited_by_count":46,"area":null},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46,"area":null},{"id":"2307.00144","title":"Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows","created":"2023-06-30","cited_by_count":45,"area":null},{"id":"2102.09972","title":"Implicit Regularization in Tensor Factorization","created":"2021-02-19","cited_by_count":44,"area":null},{"id":"2406.06158","title":"Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning","created":"2024-06-10","cited_by_count":42,"area":null},{"id":"2307.06440","title":"No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models","created":"2023-07-12","cited_by_count":41,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"area":null},{"id":"2207.10430","title":"The Neural Race Reduction: Dynamics of Abstraction in Gated Networks","created":"2022-07-21","cited_by_count":37,"area":null},{"id":"2306.13575","title":"Scaling MLPs: A Tale of Inductive Bias","created":"2023-06-23","cited_by_count":37,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2201.12680","title":"Understanding Deep Contrastive Learning via Coordinate-wise Optimization","created":"2022-01-29","cited_by_count":35,"area":null},{"id":"2210.17216","title":"Symmetries, flat minima, and the conserved quantities of gradient flow","created":"2022-10-31","cited_by_count":35,"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":"2111.13293","title":"KNAS: Green Neural Architecture Search","created":"2021-11-26","cited_by_count":33,"area":null},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2305.16038","title":"Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank","created":"2023-05-25","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2307.12851","title":"Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization","created":"2023-07-24","cited_by_count":28,"area":null},{"id":"2108.01538","title":"Geometry of Linear Convolutional Networks","created":"2021-08-03","cited_by_count":27,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2205.14612","title":"Do Residual Neural Networks discretize Neural Ordinary Differential Equations?","created":"2022-05-29","cited_by_count":27,"area":null},{"id":"2307.04204","title":"Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory","created":"2023-07-09","cited_by_count":26,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","cited_by_count":25,"area":null},{"id":"2105.14301","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","created":"2021-05-29","cited_by_count":25,"area":null},{"id":"2110.05518","title":"Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs","created":"2021-10-11","cited_by_count":25,"area":null},{"id":"2205.10637","title":"Symmetry Teleportation for Accelerated Optimization","created":"2022-05-21","cited_by_count":25,"area":null},{"id":"2112.11027","title":"More is Less: Inducing Sparsity via Overparameterization","created":"2021-12-21","cited_by_count":24,"area":null},{"id":"2110.04947","title":"Towards Demystifying Representation Learning with Non-contrastive Self-supervision","created":"2021-10-11","cited_by_count":23,"area":null},{"id":"2104.13727","title":"PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols","created":"2021-04-28","cited_by_count":22,"area":null},{"id":"2107.05074","title":"SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs","created":"2021-07-11","cited_by_count":22,"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":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2212.14457","title":"Bayesian Interpolation with Deep Linear Networks","created":"2022-12-29","cited_by_count":21,"area":null},{"id":"2305.13064","title":"Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond","created":"2023-05-22","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":"2109.03958","title":"TrAISformer -- A Transformer Network with Sparse Augmented Data Representation and Cross Entropy Loss for AIS-based Vessel Trajectory Prediction","created":"2021-09-08","cited_by_count":20,"area":null},{"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":"2403.11391","title":"Investigating the Benefits of Projection Head for Representation Learning","created":"2024-03-18","cited_by_count":20,"area":null},{"id":"2103.09404","title":"Collapsible Linear Blocks for Super-Efficient Super Resolution","created":"2021-03-17","cited_by_count":19,"area":null},{"id":"2104.05508","title":"Noether: The More Things Change, the More Stay the Same","created":"2021-04-12","cited_by_count":19,"area":null},{"id":"2205.05671","title":"RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization","created":"2022-05-11","cited_by_count":19,"area":null},{"id":"2312.00935","title":"Understanding Unimodal Bias in Multimodal Deep Linear Networks","created":"2023-12-01","cited_by_count":19,"area":null},{"id":"2209.04121","title":"Fast Neural Kernel Embeddings for General Activations","created":"2022-09-09","cited_by_count":18,"area":null},{"id":"2305.16427","title":"Neural (Tangent Kernel) Collapse","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2405.17580","title":"Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes","created":"2024-05-27","cited_by_count":18,"area":null},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17,"area":null},{"id":"2205.12101","title":"Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width","created":"2022-05-24","cited_by_count":17,"area":null},{"id":"2405.13456","title":"Deep linear networks for regression are implicitly regularized towards flat minima","created":"2024-05-22","cited_by_count":17,"area":null},{"id":"2202.00856","title":"The Role of Linear Layers in Nonlinear Interpolating Networks","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2211.00188","title":"Adaptive Compression for Communication-Efficient Distributed Training","created":"2022-10-31","cited_by_count":16,"area":null},{"id":"2301.10808","title":"Graph Neural Tangent Kernel: Convergence on Large Graphs","created":"2023-01-25","cited_by_count":16,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2401.04553","title":"Linear Recursive Feature Machines provably recover low-rank matrices","created":"2024-01-09","cited_by_count":16,"area":null},{"id":"2410.04887","title":"Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2110.03313","title":"Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2306.17499","title":"The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks","created":"2023-06-30","cited_by_count":15,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2102.07567","title":"Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent","created":"2021-02-15","cited_by_count":14,"area":null},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2107.02306","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","created":"2021-07-05","cited_by_count":14,"area":null},{"id":"2110.09548","title":"Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks","created":"2021-10-18","cited_by_count":14,"area":null},{"id":"2409.14981","title":"On The Specialization of Neural Modules","created":"2024-09-23","cited_by_count":14,"area":null},{"id":"2410.20634","title":"Plastic Learning with Deep Fourier Features","created":"2024-10-27","cited_by_count":14,"area":null},{"id":"2302.12239","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2308.12221","title":"Critical Learning Periods Emerge Even in Deep Linear Networks","created":"2023-08-23","cited_by_count":13,"area":null},{"id":"2402.07568","title":"Weisfeiler-Leman at the margin: When more expressivity matters","created":"2024-02-12","cited_by_count":13,"area":null},{"id":"2305.05448","title":"Robust Implicit Regularization via Weight Normalization","created":"2023-05-09","cited_by_count":12,"area":null}],"next_cursor":"100"}