{"total":142,"rows":[{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561,"area":null},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378,"area":null},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153,"area":null},{"id":"2109.11676","title":"Theory of overparametrization in quantum neural networks","created":"2021-09-23","cited_by_count":100,"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":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2112.15383","title":"Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs","created":"2021-12-31","cited_by_count":53,"area":null},{"id":"2107.02397","title":"Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons","created":"2021-07-06","cited_by_count":41,"area":null},{"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":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","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":"2110.03128","title":"On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications","created":"2021-10-07","cited_by_count":31,"area":null},{"id":"2409.15771","title":"Zero-shot forecasting of chaotic systems","created":"2024-09-24","cited_by_count":28,"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":"2105.03193","title":"Network Pruning That Matters: A Case Study on Retraining Variants","created":"2021-05-07","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":"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":"2203.10036","title":"On the Generalization Mystery in Deep Learning","created":"2022-03-18","cited_by_count":25,"area":null},{"id":"2112.03215","title":"Multi-scale Feature Learning Dynamics: Insights for Double Descent","created":"2021-12-06","cited_by_count":24,"area":null},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23,"area":"lr"},{"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":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2110.09771","title":"On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game","created":"2021-10-19","cited_by_count":20,"area":null},{"id":"2202.10847","title":"UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography","created":"2022-02-22","cited_by_count":19,"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":"2109.03777","title":"Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP","created":"2021-09-08","cited_by_count":17,"area":null},{"id":"2106.07724","title":"An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks","created":"2021-06-14","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":"2207.09611","title":"Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions","created":"2022-07-20","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":"2103.05524","title":"On the interplay between data structure and loss function in classification problems","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2104.07794","title":"An $L^2$ Analysis of Reinforcement Learning in High Dimensions with Kernel and Neural Network Approximation","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2110.03450","title":"Efficient and Private Federated Learning with Partially Trainable Networks","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2111.02278","title":"Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks","created":"2021-11-03","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":"2203.10736","title":"The activity-weight duality in feed forward neural networks: The geometric determinants of generalization","created":"2022-03-21","cited_by_count":12,"area":null},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2502.05300","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","created":"2025-02-07","cited_by_count":12,"area":null},{"id":"2107.04641","title":"Training Over-parameterized Models with Non-decomposable Objectives","created":"2021-07-09","cited_by_count":11,"area":null},{"id":"2404.10947","title":"Residual Connections Harm Generative Representation Learning","created":"2024-04-16","cited_by_count":11,"area":"diffusion"},{"id":"2411.18376","title":"Preserving Deep Representations In One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework","created":"2024-11-27","cited_by_count":11,"area":null},{"id":"2101.09849","title":"Deep Learning Generalization and the Convex Hull of Training Sets","created":"2021-01-25","cited_by_count":10,"area":null},{"id":"2203.06031","title":"Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2309.08044","title":"How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent","created":"2023-09-14","cited_by_count":10,"area":null},{"id":"2310.01975","title":"Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10,"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":"2201.11676","title":"Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap","created":"2022-01-27","cited_by_count":9,"area":null},{"id":"2206.09136","title":"Provable Generalization of Overparameterized Meta-learning Trained with SGD","created":"2022-06-18","cited_by_count":9,"area":null},{"id":"2306.15742","title":"Differentially Private Video Activity Recognition","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2112.01637","title":"AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning","created":"2021-12-02","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":"2509.11348","title":"On Linear Mode Connectivity of Mixture-of-Experts Architectures","created":"2025-09-14","cited_by_count":8,"area":"moe"},{"id":"2111.03505","title":"Visualizing the Emergence of Intermediate Visual Patterns in DNNs","created":"2021-11-05","cited_by_count":7,"area":null},{"id":"2403.12486","title":"NTK-Guided Few-Shot Class Incremental Learning","created":"2024-03-19","cited_by_count":7,"area":null},{"id":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2105.01867","title":"A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2107.11359","title":"Rethinking Hard-Parameter Sharing in Multi-Domain Learning","created":"2021-07-23","cited_by_count":6,"area":null},{"id":"2111.14212","title":"On Predicting Generalization using GANs","created":"2021-11-28","cited_by_count":6,"area":null},{"id":"2201.09209","title":"Weight Expansion: A New Perspective on Dropout and Generalization","created":"2022-01-23","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":"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":"2210.06143","title":"On the Importance of Gradient Norm in PAC-Bayesian Bounds","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2304.09802","title":"Generalization and Estimation Error Bounds for Model-based Neural Networks","created":"2023-04-19","cited_by_count":6,"area":null},{"id":"2305.01932","title":"Fully Automatic Neural Network Reduction for Formal Verification","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2401.12362","title":"VC dimension of Graph Neural Networks with Pfaffian activation functions","created":"2024-01-22","cited_by_count":6,"area":null},{"id":"2505.22650","title":"On Learning Verifiers and Implications to Chain-of-Thought Reasoning","created":"2025-05-28","cited_by_count":6,"area":"lr"},{"id":"2302.07828","title":"Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points","created":"2023-02-15","cited_by_count":5,"area":null},{"id":"2310.03205","title":"A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization","created":"2023-10-04","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":"2205.06304","title":"Overparameterization Improves StyleGAN Inversion","created":"2022-05-12","cited_by_count":4,"area":null},{"id":"2301.01352","title":"WLD-Reg: A Data-dependent Within-layer Diversity Regularizer","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","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":"2209.14267","title":"Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets","created":"2022-09-28","cited_by_count":3,"area":null},{"id":"2211.08900","title":"Convergence analysis of unsupervised Legendre-Galerkin neural networks for linear second-order elliptic PDEs","created":"2022-11-16","cited_by_count":3,"area":null},{"id":"2303.04338","title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2304.03385","title":"Wide neural networks: From non-gaussian random fields at initialization to the NTK geometry of training","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2404.17426","title":"One-Shot Image Restoration","created":"2024-04-26","cited_by_count":3,"area":null},{"id":"2404.17868","title":"Error analysis for finite element operator learning methods for solving parametric second-order elliptic PDEs","created":"2024-04-27","cited_by_count":3,"area":null},{"id":"2411.10649","title":"Deep Loss Convexification for Learning Iterative Models","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2503.11272","title":"When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2509.04966","title":"Neuro-Spectral Architectures for Causal Physics-Informed Networks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2606.17830","title":"Functional Equivalence in Attention: A Comprehensive Study with Applications to Linear Mode Connectivity","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2106.04795","title":"Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off","created":"2021-06-09","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":"2306.12190","title":"Quantifying lottery tickets under label noise: accuracy, calibration, and complexity","created":"2023-06-21","cited_by_count":2,"area":null},{"id":"2310.00141","title":"The Gift of Feedback: Improving ASR Model Quality by Learning from User Corrections through Federated Learning","created":"2023-09-29","cited_by_count":2,"area":null},{"id":"2310.05169","title":"Investigating the Ability of PINNs To Solve Burgers' PDE Near Finite-Time BlowUp","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2402.05356","title":"Exploring Learning Complexity for Efficient Downstream Dataset Pruning","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2402.11733","title":"The Effectiveness of Random Forgetting for Robust Generalization","created":"2024-02-18","cited_by_count":2,"area":null},{"id":"2406.10090","title":"Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2502.12508","title":"Understanding Generalization in Transformers: Error Bounds and Training Dynamics Under Benign and Harmful Overfitting","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2508.12576","title":"Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg","created":"2025-08-18","cited_by_count":2,"area":null},{"id":"2509.06314","title":"Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix","created":"2025-09-08","cited_by_count":2,"area":null}],"next_cursor":"100"}