{"total":94,"rows":[{"id":"2104.11375","title":"Decentralized Federated Averaging","created":"2021-04-23","cited_by_count":114,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2202.06526","title":"Benign Overfitting in Two-layer Convolutional Neural Networks","created":"2022-02-14","cited_by_count":91,"area":null},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88,"area":"distill"},{"id":"2202.12040","title":"Self-Training: A Survey","created":"2022-02-24","cited_by_count":86,"area":null},{"id":"2304.06648","title":"DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning","created":"2023-04-13","cited_by_count":84,"area":"diffusion"},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2209.14863","title":"Neural Networks Efficiently Learn Low-Dimensional Representations with SGD","created":"2022-09-29","cited_by_count":63,"area":null},{"id":"2102.02410","title":"A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network","created":"2021-02-04","cited_by_count":47,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2307.05014","title":"Test-Time Training on Video Streams","created":"2023-07-11","cited_by_count":37,"area":null},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2302.05933","title":"Generalization Ability of Wide Neural Networks on $\\mathbb{R}$","created":"2023-02-12","cited_by_count":30,"area":null},{"id":"2306.04933","title":"InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding","created":"2023-06-08","cited_by_count":30,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2202.05258","title":"Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks","created":"2022-02-10","cited_by_count":28,"area":null},{"id":"2212.03714","title":"Reconstructing Training Data from Model Gradient, Provably","created":"2022-12-07","cited_by_count":27,"area":null},{"id":"2302.10034","title":"Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron","created":"2023-02-20","cited_by_count":25,"area":null},{"id":"2112.12982","title":"Parameter identifiability of a deep feedforward ReLU neural network","created":"2021-12-24","cited_by_count":24,"area":null},{"id":"2110.09246","title":"Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection","created":"2021-10-18","cited_by_count":23,"area":null},{"id":"2207.03584","title":"Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling","created":"2022-07-07","cited_by_count":23,"area":null},{"id":"2110.02479","title":"Exponentially Many Local Minima in Quantum Neural Networks","created":"2021-10-06","cited_by_count":22,"area":null},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21,"area":null},{"id":"2405.16646","title":"A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts","created":"2024-05-26","cited_by_count":21,"area":"moe"},{"id":"2106.10744","title":"On the Cryptographic Hardness of Learning Single Periodic Neurons","created":"2021-06-20","cited_by_count":20,"area":null},{"id":"2101.02533","title":"Towards Understanding Learning in Neural Networks with Linear Teachers","created":"2021-01-07","cited_by_count":19,"area":null},{"id":"2201.08514","title":"How does unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis","created":"2022-01-21","cited_by_count":19,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2106.06251","title":"On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting","created":"2021-06-11","cited_by_count":16,"area":"distill"},{"id":"2302.02922","title":"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks","created":"2023-02-06","cited_by_count":16,"area":null},{"id":"2206.12802","title":"Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis","created":"2022-06-26","cited_by_count":15,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2304.10524","title":"Learning Narrow One-Hidden-Layer ReLU Networks","created":"2023-04-20","cited_by_count":14,"area":null},{"id":"2406.01977","title":"What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding","created":"2024-06-04","cited_by_count":14,"area":null},{"id":"1802.07417","title":"Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms","created":"2018-02-21","cited_by_count":13,"area":"moe"},{"id":"2206.07424","title":"Local Identifiability of Deep ReLU Neural Networks: the Theory","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2208.02711","title":"Agnostic Learning of General ReLU Activation Using Gradient Descent","created":"2022-08-04","cited_by_count":12,"area":null},{"id":"2412.18040","title":"Theoretical Constraints on the Expressive Power of $\\mathsf{RoPE}$-based Tensor Attention Transformers","created":"2024-12-23","cited_by_count":12,"area":null},{"id":"2403.06392","title":"Towards Robust Out-of-Distribution Generalization Bounds via Sharpness","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2107.10868","title":"Local SGD Optimizes Overparameterized Neural Networks in Polynomial Time","created":"2021-07-22","cited_by_count":10,"area":null},{"id":"2205.14818","title":"Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods","created":"2022-05-30","cited_by_count":10,"area":"distill"},{"id":"2302.07426","title":"Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy","created":"2023-02-15","cited_by_count":10,"area":null},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"area":null},{"id":"2210.06088","title":"Annihilation of Spurious Minima in Two-Layer ReLU Networks","created":"2022-10-12","cited_by_count":9,"area":null},{"id":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9,"area":null},{"id":"2101.07150","title":"Stable Recovery of Entangled Weights: Towards Robust Identification of Deep Neural Networks from Minimal Samples","created":"2021-01-18","cited_by_count":8,"area":null},{"id":"2207.03615","title":"Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data","created":"2022-07-07","cited_by_count":8,"area":null},{"id":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2110.15821","title":"Landscape analysis of an improved power method for tensor decomposition","created":"2021-10-29","cited_by_count":7,"area":null},{"id":"2307.12496","title":"A faster and simpler algorithm for learning shallow networks","created":"2023-07-24","cited_by_count":7,"area":null},{"id":"2403.08121","title":"Early Directional Convergence in Deep Homogeneous Neural Networks for Small Initializations","created":"2024-03-12","cited_by_count":7,"area":null},{"id":"2111.04727","title":"Efficiently Learning Any One Hidden Layer ReLU Network From Queries","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2311.13624","title":"A Theoretical Insight into Attack and Defense of Gradient Leakage in Transformer","created":"2023-11-22","cited_by_count":6,"area":null},{"id":"2402.09478","title":"Data Reconstruction Attacks and Defenses: A Systematic Evaluation","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2403.07310","title":"How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2411.15669","title":"Implicit High-Order Moment Tensor Estimation and Learning Latent Variable Models","created":"2024-11-23","cited_by_count":6,"area":null},{"id":"2201.04545","title":"On generalization bounds for deep networks based on loss surface implicit regularization","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2206.02139","title":"Early Stage Convergence and Global Convergence of Training Mildly Parameterized Neural Networks","created":"2022-06-05","cited_by_count":5,"area":null},{"id":"2210.11452","title":"Global Convergence of SGD On Two Layer Neural Nets","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2211.04589","title":"Finite Sample Identification of Wide Shallow Neural Networks with Biases","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"id":"2206.05904","title":"Theoretical guarantees for the advantage of GNNs over NNs in generalizing bandlimited functions on Euclidean cubes","created":"2022-06-13","cited_by_count":4,"area":null},{"id":"2305.00322","title":"Toward $L_\\infty$-recovery of Nonlinear Functions: A Polynomial Sample Complexity Bound for Gaussian Random Fields","created":"2023-04-29","cited_by_count":4,"area":null},{"id":"2307.12840","title":"Efficiently Learning One-Hidden-Layer ReLU Networks via Schur Polynomials","created":"2023-07-24","cited_by_count":4,"area":null},{"id":"2502.16021","title":"Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2104.11895","title":"Achieving Small Test Error in Mildly Overparameterized Neural Networks","created":"2021-04-24","cited_by_count":3,"area":null},{"id":"2209.15265","title":"Overparameterized ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2308.08070","title":"Max-affine regression via first-order methods","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2309.09258","title":"Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets","created":"2023-09-17","cited_by_count":3,"area":null},{"id":"2101.06511","title":"Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems","created":"2021-01-16","cited_by_count":2,"area":null},{"id":"2209.08627","title":"Is Stochastic Gradient Descent Near Optimal?","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2305.16508","title":"Most Neural Networks Are Almost Learnable","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2312.16819","title":"Hidden Minima in Two-Layer ReLU Networks","created":"2023-12-28","cited_by_count":2,"area":null},{"id":"2503.11108","title":"Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding","created":"2025-03-14","cited_by_count":2,"area":"inference"},{"id":"2508.18408","title":"Low-Rank Tensor Decompositions for the Theory of Neural Networks","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2510.00399","title":"How Can Mamba Learn In Context with Outliers and Generalize Provably?","created":"2025-10-01","cited_by_count":2,"area":"ssm"},{"id":"2203.16455","title":"Explicitising The Implicit Intrepretability of Deep Neural Networks Via Duality","created":"2022-03-01","cited_by_count":1,"area":null},{"id":"2410.03477","title":"On the Hardness of Learning One Hidden Layer Neural Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2502.05574","title":"Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark","created":"2025-02-08","cited_by_count":1,"area":"distill"},{"id":"2503.10428","title":"Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2512.15987","title":"Provably Extracting the Features from a General Superposition","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2606.04476","title":"When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2201.07934","title":"Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks","created":"2022-01-03","cited_by_count":0,"area":null},{"id":"2302.01976","title":"SPARLING: Learning Latent Representations with Extremely Sparse Activations","created":"2023-02-03","cited_by_count":0,"area":null},{"id":"2306.06582","title":"Fast, Distribution-free Predictive Inference for Neural Networks with Coverage Guarantees","created":"2023-06-11","cited_by_count":0,"area":null},{"id":"2307.08880","title":"Modular Neural Network Approaches for Surgical Image Recognition","created":"2023-07-17","cited_by_count":0,"area":null},{"id":"2406.18035","title":"Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2507.05533","title":"Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.19382","title":"A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2609.34667","title":"Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}