{"total":290,"rows":[{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313,"area":"mechinterp"},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"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":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86,"area":null},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84,"area":null},{"id":"2109.09444","title":"When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?","created":"2021-09-20","cited_by_count":58,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55,"area":null},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54,"area":"mllm"},{"id":"2302.04451","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","created":"2023-02-09","cited_by_count":40,"area":null},{"id":"2103.15209","title":"Understanding the role of importance weighting for deep learning","created":"2021-03-28","cited_by_count":39,"area":null},{"id":"2311.01796","title":"Learning to Augment Distributions for Out-of-Distribution Detection","created":"2023-11-03","cited_by_count":38,"area":null},{"id":"2107.13171","title":"Learning with Multiclass AUC: Theory and Algorithms","created":"2021-07-28","cited_by_count":35,"area":null},{"id":"2104.05641","title":"Generalization bounds via distillation","created":"2021-04-12","cited_by_count":34,"area":null},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2202.12891","title":"Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects","created":"2022-02-25","cited_by_count":32,"area":null},{"id":"2310.13088","title":"Sequence Length Independent Norm-Based Generalization Bounds for Transformers","created":"2023-10-19","cited_by_count":29,"area":null},{"id":"2104.01086","title":"Defending Against Image Corruptions Through Adversarial Augmentations","created":"2021-04-02","cited_by_count":28,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2107.12723","title":"Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel","created":"2021-07-27","cited_by_count":26,"area":null},{"id":"2101.06154","title":"On the statistical complexity of quantum circuits","created":"2021-01-15","cited_by_count":25,"area":null},{"id":"2106.03314","title":"Measuring Generalization with Optimal Transport","created":"2021-06-07","cited_by_count":25,"area":null},{"id":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2302.12383","title":"Generalization Analysis for Contrastive Representation Learning","created":"2023-02-24","cited_by_count":25,"area":null},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25,"area":null},{"id":"2306.08321","title":"Nonparametric regression using over-parameterized shallow ReLU neural networks","created":"2023-06-14","cited_by_count":24,"area":null},{"id":"2103.02200","title":"Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations","created":"2021-03-03","cited_by_count":22,"area":null},{"id":"2111.05529","title":"Understanding the Generalization Benefit of Model Invariance from a Data Perspective","created":"2021-11-10","cited_by_count":22,"area":null},{"id":"2201.09418","title":"Approximation bounds for norm constrained neural networks with applications to regression and GANs","created":"2022-01-24","cited_by_count":22,"area":null},{"id":"2105.14989","title":"Representation Learning Beyond Linear Prediction Functions","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2209.09298","title":"Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"area":null},{"id":"2305.06648","title":"Generalization bounds for neural ordinary differential equations and deep residual networks","created":"2023-05-11","cited_by_count":21,"area":null},{"id":"2311.13184","title":"Large Language Model-Enhanced Algorithm Selection: Towards Comprehensive Algorithm Representation","created":"2023-11-22","cited_by_count":21,"area":null},{"id":"2111.14932","title":"Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection","created":"2021-11-29","cited_by_count":20,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2501.13329","title":"Sparse identification of nonlinear dynamics and Koopman operators with Shallow Recurrent Decoder Networks","created":"2025-01-23","cited_by_count":20,"area":null},{"id":"2102.06879","title":"Learning from Similarity-Confidence Data","created":"2021-02-13","cited_by_count":19,"area":null},{"id":"2309.13658","title":"Fantastic Generalization Measures are Nowhere to be Found","created":"2023-09-24","cited_by_count":19,"area":null},{"id":"2210.13150","title":"A PAC-Bayesian Generalization Bound for Equivariant Networks","created":"2022-10-24","cited_by_count":18,"area":null},{"id":"2211.14966","title":"Adversarial Rademacher Complexity of Deep Neural Networks","created":"2022-11-27","cited_by_count":18,"area":null},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2102.10234","title":"Generalization bounds for graph convolutional neural networks via Rademacher complexity","created":"2021-02-20","cited_by_count":17,"area":null},{"id":"2401.01623","title":"Can AI Be as Creative as Humans?","created":"2024-01-03","cited_by_count":17,"area":null},{"id":"2208.04284","title":"On Rademacher Complexity-based Generalization Bounds for Deep Learning","created":"2022-08-08","cited_by_count":16,"area":null},{"id":"2210.11530","title":"Theoretical analysis of deep neural networks for temporally dependent observations","created":"2022-10-20","cited_by_count":16,"area":null},{"id":"2103.05959","title":"Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones","created":"2021-03-10","cited_by_count":15,"area":"distill"},{"id":"2304.01561","title":"Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression","created":"2023-04-04","cited_by_count":15,"area":null},{"id":"2104.14132","title":"Generalization Guarantees for Neural Architecture Search with Train-Validation Split","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2206.03299","title":"Generalization Error Bounds for Deep Neural Networks Trained by SGD","created":"2022-06-07","cited_by_count":14,"area":null},{"id":"2103.04554","title":"Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models","created":"2021-03-08","cited_by_count":13,"area":null},{"id":"2111.04901","title":"Label-Aware Distribution Calibration for Long-tailed Classification","created":"2021-11-09","cited_by_count":13,"area":null},{"id":"2211.01258","title":"Instance-Dependent Generalization Bounds via Optimal Transport","created":"2022-11-02","cited_by_count":13,"area":null},{"id":"2310.05632","title":"Binary Classification with Confidence Difference","created":"2023-10-09","cited_by_count":13,"area":null},{"id":"2202.09028","title":"On the Implicit Bias Towards Minimal Depth of Deep Neural Networks","created":"2022-02-18","cited_by_count":12,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2112.04364","title":"Generalization Error Bounds for Iterative Recovery Algorithms Unfolded as Neural Networks","created":"2021-12-08","cited_by_count":11,"area":null},{"id":"2202.13216","title":"Adversarial robustness of sparse local Lipschitz predictors","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2306.03116","title":"Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds","created":"2023-06-05","cited_by_count":11,"area":null},{"id":"2309.11617","title":"Statistical Complexity of Quantum Learning","created":"2023-09-20","cited_by_count":11,"area":null},{"id":"2505.12601","title":"Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers","created":"2025-05-19","cited_by_count":11,"area":"lr"},{"id":"2202.06233","title":"The Sample Complexity of One-Hidden-Layer Neural Networks","created":"2022-02-13","cited_by_count":10,"area":null},{"id":"2310.01225","title":"A path-norm toolkit for modern networks: consequences, promises and challenges","created":"2023-10-02","cited_by_count":10,"area":null},{"id":"2311.15502","title":"Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical","created":"2023-11-27","cited_by_count":10,"area":null},{"id":"2404.03176","title":"Information-Theoretic Generalization Bounds for Deep Neural Networks","created":"2024-04-04","cited_by_count":10,"area":null},{"id":"2102.03282","title":"Effects of quantum resources on the statistical complexity of quantum circuits","created":"2021-02-05","cited_by_count":9,"area":null},{"id":"2103.00719","title":"LocalDrop: A Hybrid Regularization for Deep Neural Networks","created":"2021-03-01","cited_by_count":9,"area":null},{"id":"2107.02378","title":"Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks","created":"2021-07-06","cited_by_count":9,"area":null},{"id":"2109.12960","title":"Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions","created":"2021-09-27","cited_by_count":9,"area":null},{"id":"2202.08070","title":"On Measuring Excess Capacity in Neural Networks","created":"2022-02-16","cited_by_count":9,"area":null},{"id":"2203.12330","title":"Predicting the generalization gap in neural networks using topological data analysis","created":"2022-03-23","cited_by_count":9,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2209.12611","title":"MaxMatch: Semi-Supervised Learning with Worst-Case Consistency","created":"2022-09-26","cited_by_count":9,"area":null},{"id":"2212.05427","title":"Statistical guarantees for sparse deep learning","created":"2022-12-11","cited_by_count":9,"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":"2305.16891","title":"Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks","created":"2023-05-26","cited_by_count":9,"area":null},{"id":"2310.06182","title":"PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2310.17154","title":"Deep Imbalanced Regression via Hierarchical Classification Adjustment","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2110.12141","title":"Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives","created":"2021-10-23","cited_by_count":8,"area":null},{"id":"2112.12303","title":"Learning with Proper Partial Labels","created":"2021-12-23","cited_by_count":8,"area":null},{"id":"2302.11085","title":"Learning to Generalize Provably in Learning to Optimize","created":"2023-02-22","cited_by_count":8,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2307.00426","title":"Sparsity-aware generalization theory for deep neural networks","created":"2023-07-01","cited_by_count":8,"area":null},{"id":"2106.04770","title":"Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space","created":"2021-06-09","cited_by_count":7,"area":null},{"id":"2107.05045","title":"Positive-Unlabeled Classification under Class-Prior Shift: A Prior-invariant Approach Based on Density Ratio Estimation","created":"2021-07-11","cited_by_count":7,"area":null},{"id":"2206.06593","title":"On Finite-Sample Identifiability of Contrastive Learning-Based Nonlinear Independent Component Analysis","created":"2022-06-14","cited_by_count":7,"area":null},{"id":"2212.12532","title":"Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers","created":"2022-12-23","cited_by_count":7,"area":null},{"id":"2301.12033","title":"Norm-based Generalization Bounds for Compositionally Sparse Neural Networks","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2305.13588","title":"Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","cited_by_count":7,"area":"distill"},{"id":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2410.10024","title":"Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2508.16082","title":"On Task Vectors and Gradients","created":"2025-08-22","cited_by_count":7,"area":null},{"id":"2203.00246","title":"An Information-Theoretic Framework for Supervised Learning","created":"2022-03-01","cited_by_count":6,"area":null},{"id":"2205.11359","title":"Towards Size-Independent Generalization Bounds for Deep Operator Nets","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2206.07892","title":"Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2207.01555","title":"Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization","created":"2022-07-04","cited_by_count":6,"area":null}],"next_cursor":"100"}