{"total":141,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638,"area":null},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2301.11526","title":"Direct Parameterization of Lipschitz-Bounded Deep Networks","created":"2023-01-27","cited_by_count":51,"area":null},{"id":"2110.03187","title":"On the Optimal Memorization Power of ReLU Neural Networks","created":"2021-10-07","cited_by_count":40,"area":null},{"id":"2205.09723","title":"Robust and Efficient Medical Imaging with Self-Supervision","created":"2022-05-19","cited_by_count":40,"area":null},{"id":"2209.13083","title":"Why neural networks find simple solutions: the many regularizers of geometric complexity","created":"2022-09-27","cited_by_count":39,"area":null},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2304.09856","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","created":"2023-04-19","cited_by_count":34,"area":null},{"id":"2203.05071","title":"On the influence of over-parameterization in manifold based surrogates and deep neural operators","created":"2022-03-09","cited_by_count":29,"area":null},{"id":"2106.12611","title":"Adversarial Examples in Multi-Layer Random ReLU Networks","created":"2021-06-23","cited_by_count":26,"area":null},{"id":"2302.10886","title":"Some Fundamental Aspects about Lipschitz Continuity of Neural Networks","created":"2023-02-21","cited_by_count":26,"area":null},{"id":"2205.09988","title":"SALTED: A Framework for SAlient Long-Tail Translation Error Detection","created":"2022-05-20","cited_by_count":23,"area":null},{"id":"2205.13863","title":"Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power","created":"2022-05-27","cited_by_count":23,"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":"2110.05626","title":"Parameterizing Activation Functions for Adversarial Robustness","created":"2021-10-11","cited_by_count":22,"area":null},{"id":"2204.06274","title":"Overparameterized Linear Regression under Adversarial Attacks","created":"2022-04-13","cited_by_count":21,"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":"2311.14646","title":"More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory","created":"2023-11-24","cited_by_count":18,"area":null},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18,"area":null},{"id":"2202.05808","title":"Investigating Power laws in Deep Representation Learning","created":"2022-02-11","cited_by_count":17,"area":null},{"id":"2202.01268","title":"DASHA: Distributed Nonconvex Optimization with Communication Compression, Optimal Oracle Complexity, and No Client Synchronization","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2203.01212","title":"A Quantitative Geometric Approach to Neural-Network Smoothness","created":"2022-03-02","cited_by_count":16,"area":null},{"id":"2204.01368","title":"Training Fully Connected Neural Networks is $\\exists\\mathbb{R}$-Complete","created":"2022-04-04","cited_by_count":15,"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":"2301.12549","title":"Unlocking Deterministic Robustness Certification on ImageNet","created":"2023-01-29","cited_by_count":13,"area":null},{"id":"2302.01629","title":"Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels","created":"2023-02-03","cited_by_count":13,"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":"2112.07324","title":"On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training","created":"2021-12-14","cited_by_count":11,"area":null},{"id":"2203.11864","title":"On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes","created":"2022-03-22","cited_by_count":11,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2305.12100","title":"How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features","created":"2023-05-20","cited_by_count":11,"area":null},{"id":"2207.03920","title":"Towards Semantic Communication Protocols: A Probabilistic Logic Perspective","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2302.05823","title":"Data efficiency and extrapolation trends in neural network interatomic potentials","created":"2023-02-12","cited_by_count":10,"area":null},{"id":"2310.20579","title":"Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks","created":"2023-10-31","cited_by_count":10,"area":null},{"id":"2202.11592","title":"A Law of Robustness beyond Isoperimetry","created":"2022-02-23","cited_by_count":9,"area":null},{"id":"2203.00849","title":"Adversarially Robust Learning with Tolerance","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2209.14881","title":"Sequential Attention for Feature Selection","created":"2022-09-29","cited_by_count":9,"area":null},{"id":"2401.12236","title":"The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness","created":"2024-01-19","cited_by_count":9,"area":null},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2204.12560","title":"Process Knowledge-infused Learning for Suicidality Assessment on Social Media","created":"2022-04-26","cited_by_count":8,"area":null},{"id":"2207.03933","title":"A law of adversarial risk, interpolation, and label noise","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","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":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2403.07264","title":"Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization","created":"2024-03-12","cited_by_count":8,"area":null},{"id":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2204.07373","title":"Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning","created":"2022-04-15","cited_by_count":7,"area":null},{"id":"2207.11621","title":"A Universal Trade-off Between the Model Size, Test Loss, and Training Loss of Linear Predictors","created":"2022-07-23","cited_by_count":7,"area":null},{"id":"2209.15106","title":"Restricted Strong Convexity of Deep Learning Models with Smooth Activations","created":"2022-09-29","cited_by_count":7,"area":null},{"id":"2305.14683","title":"On progressive sharpening, flat minima and generalisation","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2306.03229","title":"Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2310.09506","title":"Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches","created":"2023-10-14","cited_by_count":7,"area":null},{"id":"2110.07807","title":"Provable Regret Bounds for Deep Online Learning and Control","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2206.04569","title":"Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2208.03835","title":"On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks","created":"2022-08-07","cited_by_count":6,"area":null},{"id":"2210.12924","title":"OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2303.04887","title":"Memory-adaptive Depth-wise Heterogeneous Federated Learning","created":"2023-03-08","cited_by_count":6,"area":null},{"id":"2308.06338","title":"Size Lowerbounds for Deep Operator Networks","created":"2023-08-11","cited_by_count":6,"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":"2308.00824","title":"An Exact Kernel Equivalence for Finite Classification Models","created":"2023-08-01","cited_by_count":5,"area":null},{"id":"2309.04708","title":"UnitModule: A Lightweight Joint Image Enhancement Module for Underwater Object Detection","created":"2023-09-09","cited_by_count":5,"area":null},{"id":"2402.02969","title":"Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random Features","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2505.19145","title":"Do Large Language Models (Really) Need Statistical Foundations?","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2509.24510","title":"Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2106.06012","title":"Learning distinct features helps, provably","created":"2021-06-10","cited_by_count":4,"area":null},{"id":"2203.13779","title":"Origins of Low-dimensional Adversarial Perturbations","created":"2022-03-25","cited_by_count":4,"area":null},{"id":"2205.01493","title":"On the uncertainty principle of neural networks","created":"2022-05-03","cited_by_count":4,"area":null},{"id":"2205.06304","title":"Overparameterization Improves StyleGAN Inversion","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2210.00301","title":"Learning Globally Smooth Functions on Manifolds","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2301.08842","title":"Limitations of Piecewise Linearity for Efficient Robustness Certification","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2305.17148","title":"Differentially Private Low-dimensional Synthetic Data from High-dimensional Datasets","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2310.00154","title":"Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2310.02513","title":"A Recipe for Improved Certifiable Robustness","created":"2023-10-04","cited_by_count":4,"area":null},{"id":"2402.08012","title":"Online Differentially Private Synthetic Data Generation","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2405.15706","title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2405.16639","title":"A direct proof of a unified law of robustness for Bregman divergence losses","created":"2024-05-26","cited_by_count":4,"area":null},{"id":"2112.07344","title":"SCORE: Approximating Curvature Information under Self-Concordant Regularization","created":"2021-12-14","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":"2206.03727","title":"Wavelet Regularization Benefits Adversarial Training","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2211.16187","title":"Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2212.08967","title":"Foundation models in brief: A historical, socio-technical focus","created":"2022-12-17","cited_by_count":3,"area":null},{"id":"2302.00775","title":"Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2305.18508","title":"On the Variance, Admissibility, and Stability of Empirical Risk Minimization","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2312.10088","title":"On Robustness to Missing Video for Audiovisual Speech Recognition","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2404.08285","title":"A Survey of Neural Network Robustness Assessment in Image Recognition","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2410.19361","title":"Engineering Trustworthy AI: A Developer Guide for Empirical Risk Minimization","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2509.22214","title":"A Law of Data Reconstruction for Random Features (and Beyond)","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2602.11175","title":"Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2202.04837","title":"Heterogeneous Calibration: A post-hoc model-agnostic framework for improved generalization","created":"2022-02-10","cited_by_count":2,"area":null},{"id":"2211.06860","title":"An Adaptive and Stability-Promoting Layerwise Training Approach for Sparse Deep Neural Network Architecture","created":"2022-11-13","cited_by_count":2,"area":null},{"id":"2303.07203","title":"On the Robustness of Text Vectorizers","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2308.00556","title":"Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2309.00771","title":"Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models","created":"2023-09-02","cited_by_count":2,"area":null},{"id":"2309.17401","title":"Adversarial Attacks to Latent Representations of Distributed Neural Networks in Split Computing","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2311.01356","title":"Upper and lower bounds for the Lipschitz constant of random neural networks","created":"2023-11-02","cited_by_count":2,"area":null}],"next_cursor":"100"}