{"total":95,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"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":"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":"2212.07469","title":"Learning threshold neurons via the \"edge of stability\"","created":"2022-12-14","cited_by_count":51,"area":null},{"id":"2108.11371","title":"Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2206.01717","title":"A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features","created":"2022-06-03","cited_by_count":49,"area":null},{"id":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"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":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2402.04980","title":"Asymptotics of feature learning in two-layer networks after one gradient-step","created":"2024-02-07","cited_by_count":38,"area":null},{"id":"2106.02105","title":"A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2303.04145","title":"Benign Overfitting for Two-layer ReLU Convolutional Neural Networks","created":"2023-03-07","cited_by_count":34,"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":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2310.07269","title":"Why Does Sharpness-Aware Minimization Generalize Better Than SGD?","created":"2023-10-11","cited_by_count":28,"area":null},{"id":"2202.04347","title":"Gradient Methods Provably Converge to Non-Robust Networks","created":"2022-02-09","cited_by_count":27,"area":null},{"id":"2104.03863","title":"A single gradient step finds adversarial examples on random two-layers neural networks","created":"2021-04-08","cited_by_count":26,"area":null},{"id":"2303.01456","title":"The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks","created":"2023-03-02","cited_by_count":23,"area":null},{"id":"2210.05577","title":"What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2103.08187","title":"Adversarial Training is Not Ready for Robot Learning","created":"2021-03-15","cited_by_count":20,"area":null},{"id":"2303.08433","title":"The Benefits of Mixup for Feature Learning","created":"2023-03-15","cited_by_count":19,"area":null},{"id":"2203.01572","title":"Data Augmentation as Feature Manipulation","created":"2022-03-03","cited_by_count":18,"area":null},{"id":"2206.03826","title":"Towards Understanding Why Mask-Reconstruction Pretraining Helps in Downstream Tasks","created":"2022-06-08","cited_by_count":18,"area":null},{"id":"2209.07263","title":"Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)","created":"2022-09-15","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":"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":"2102.03716","title":"SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation","created":"2021-02-07","cited_by_count":16,"area":null},{"id":"2207.11727","title":"Can we achieve robustness from data alone?","created":"2022-07-24","cited_by_count":16,"area":null},{"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":"2210.12030","title":"Evolution of Neural Tangent Kernels under Benign and Adversarial Training","created":"2022-10-21","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":"2410.08194","title":"Features are fate: a theory of transfer learning in high-dimensional regression","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2306.13926","title":"Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons","created":"2023-06-24","cited_by_count":12,"area":null},{"id":"2410.08503","title":"Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data","created":"2024-10-11","cited_by_count":12,"area":null},{"id":"2112.15250","title":"Benign Overfitting in Adversarially Robust Linear Classification","created":"2021-12-31","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":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2406.17338","title":"Robustly Optimized Deep Feature Decoupling Network for Fatty Liver Diseases Detection","created":"2024-06-25","cited_by_count":11,"area":null},{"id":"2109.14213","title":"On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization","created":"2021-09-29","cited_by_count":9,"area":null},{"id":"2208.01220","title":"GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction","created":"2022-08-02","cited_by_count":8,"area":null},{"id":"2210.12606","title":"Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2303.00783","title":"Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2102.05110","title":"Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2106.07814","title":"Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity","created":"2021-06-15","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":"2102.04057","title":"Improving filling level classification with adversarial training","created":"2021-02-08","cited_by_count":5,"area":null},{"id":"2206.12963","title":"Self-Healing Robust Neural Networks via Closed-Loop Control","created":"2022-06-26","cited_by_count":5,"area":null},{"id":"2211.08686","title":"Improving Interpretability via Regularization of Neural Activation Sensitivity","created":"2022-11-16","cited_by_count":5,"area":null},{"id":"2306.01271","title":"On the Clean Generalization and Robust Overfitting in Adversarial Training from Two Theoretical Views: Representation Complexity and Training Dynamics","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2306.04793","title":"On the Joint Interaction of Models, Data, and Features","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2311.10992","title":"Towards Robust and Accurate Visual Prompting","created":"2023-11-18","cited_by_count":5,"area":null},{"id":"2410.11206","title":"Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2202.06996","title":"Unlabeled Data Help: Minimax Analysis and Adversarial Robustness","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2209.08647","title":"Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness","created":"2022-09-18","cited_by_count":4,"area":null},{"id":"2505.18909","title":"On the Role of Label Noise in the Feature Learning Process","created":"2025-05-25","cited_by_count":4,"area":null},{"id":"2510.17526","title":"How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2511.22270","title":"Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs","created":"2025-11-27","cited_by_count":4,"area":null},{"id":"2103.15385","title":"Lagrangian Objective Function Leads to Improved Unforeseen Attack Generalization in Adversarial Training","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2108.13602","title":"How Does Adversarial Fine-Tuning Benefit BERT?","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2205.09860","title":"Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2301.00335","title":"Pruning Before Training May Improve Generalization, Provably","created":"2023-01-01","cited_by_count":3,"area":null},{"id":"2303.16887","title":"Towards Understanding the Effect of Pretraining Label Granularity","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2402.08768","title":"Adversarially Robust Feature Learning for Breast Cancer Diagnosis","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2511.18006","title":"Understanding Private Learning From Feature Perspective","created":"2025-11-22","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2102.08093","title":"A Law of Robustness for Weight-bounded Neural Networks","created":"2021-02-16","cited_by_count":2,"area":null},{"id":"2308.03215","title":"The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning","created":"2023-08-06","cited_by_count":2,"area":null},{"id":"2405.16036","title":"Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustness","created":"2024-05-25","cited_by_count":2,"area":null},{"id":"2208.06918","title":"Gradient Mask: Lateral Inhibition Mechanism Improves Performance in Artificial Neural Networks","created":"2022-08-14","cited_by_count":1,"area":null},{"id":"2209.02408","title":"Robustness and invariance properties of image classifiers","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2304.05895","title":"Towards Understanding How Data Augmentation Works with Imbalanced Data","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2403.16176","title":"Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2406.16200","title":"Feature compression is the root cause of adversarial fragility in neural network classifiers","created":"2024-06-23","cited_by_count":1,"area":null},{"id":"2502.16076","title":"Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2506.24120","title":"Data Uniformity Improves Training Efficiency and More, with a Convergence Framework Beyond the NTK Regime","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2602.02767","title":"Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.03872","title":"Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.06549","title":"Refining the Information Bottleneck via Adversarial Information Separation","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.04881","title":"Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2605.26929","title":"When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2103.10603","title":"Noise Modulation: Let Your Model Interpret Itself","created":"2021-03-19","cited_by_count":0,"area":null},{"id":"2404.01642","title":"Patch Synthesis for Property Repair of Deep Neural Networks","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2404.19567","title":"Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2406.06792","title":"Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2409.17592","title":"Deep Manifold Part 1: Anatomy of Neural Network Manifold","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.13193","title":"Golyadkin's Torment: Doppelg\\\"angers and Adversarial Vulnerability","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2502.17972","title":"Model-Free Adversarial Purification via Coarse-To-Fine Tensor Network Representation","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2503.04111","title":"Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2504.00038","title":"Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2504.10850","title":"How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2506.06823","title":"Exploring Visual Prompting: Robustness Inheritance and Beyond","created":"2025-06-07","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":"2508.11432","title":"Robust Convolution Neural ODEs via Contractivity-promoting regularization","created":"2025-08-15","cited_by_count":0,"area":null}],"next_cursor":null}