{"total":80,"rows":[{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"area":null},{"id":"2203.15046","title":"AUC Maximization in the Era of Big Data and AI: A Survey","created":"2022-03-28","cited_by_count":100,"area":null},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2205.07344","title":"Policy Gradient Method For Robust Reinforcement Learning","created":"2022-05-15","cited_by_count":69,"area":null},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2210.05775","title":"C-Mixup: Improving Generalization in Regression","created":"2022-10-11","cited_by_count":57,"area":null},{"id":"2304.00488","title":"Saddle-to-Saddle Dynamics in Diagonal Linear Networks","created":"2023-04-02","cited_by_count":57,"area":null},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2307.00144","title":"Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows","created":"2023-06-30","cited_by_count":45,"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":"2111.03741","title":"Sharp Bounds for Federated Averaging (Local SGD) and Continuous Perspective","created":"2021-11-05","cited_by_count":38,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2305.18764","title":"When Does Optimizing a Proper Loss Yield Calibration?","created":"2023-05-30","cited_by_count":36,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2302.00849","title":"Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent","created":"2023-02-02","cited_by_count":25,"area":null},{"id":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2205.09072","title":"On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias","created":"2022-05-18","cited_by_count":21,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2401.07187","title":"A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Models","created":"2024-01-14","cited_by_count":20,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15,"area":null},{"id":"2106.10820","title":"Stateful ODE-Nets using Basis Function Expansions","created":"2021-06-21","cited_by_count":14,"area":null},{"id":"2202.08325","title":"A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments","created":"2022-02-16","cited_by_count":14,"area":null},{"id":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2207.05685","title":"PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners","created":"2022-07-12","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":"2307.07785","title":"The Interpolating Information Criterion for Overparameterized Models","created":"2023-07-15","cited_by_count":12,"area":null},{"id":"2105.06569","title":"The Dynamics of Gradient Descent for Overparametrized Neural Networks","created":"2021-05-13","cited_by_count":11,"area":null},{"id":"2112.15250","title":"Benign Overfitting in Adversarially Robust Linear Classification","created":"2021-12-31","cited_by_count":11,"area":null},{"id":"2506.14202","title":"DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2210.04389","title":"DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning","created":"2022-10-10","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":"2405.01725","title":"Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2306.09478","title":"Understanding and Mitigating Extrapolation Failures in Physics-Informed Neural Networks","created":"2023-06-15","cited_by_count":9,"area":null},{"id":"2104.02836","title":"Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2310.09183","title":"PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning","created":"2023-10-13","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":"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":"2207.04612","title":"Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm","created":"2022-07-11","cited_by_count":6,"area":null},{"id":"2305.15901","title":"Consistent Optimal Transport with Empirical Conditional Measures","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2202.05068","title":"Controlling the Complexity and Lipschitz Constant improves polynomial nets","created":"2022-02-10","cited_by_count":5,"area":null},{"id":"2311.07013","title":"A PAC-Bayesian Perspective on the Interpolating Information Criterion","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2106.05397","title":"From inexact optimization to learning via gradient concentration","created":"2021-06-09","cited_by_count":4,"area":null},{"id":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2305.11417","title":"Exploring the Complexity of Deep Neural Networks through Functional Equivalence","created":"2023-05-19","cited_by_count":4,"area":null},{"id":"2405.11743","title":"A General Theory for Compositional Generalization","created":"2024-05-20","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":"2409.05800","title":"Input Space Mode Connectivity in Deep Neural Networks","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2503.13145","title":"High-entropy Advantage in Neural Networks' Generalizability","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2202.11099","title":"Rotationally Equivariant Super-Resolution of Velocity Fields in Two-Dimensional Fluids Using Convolutional Neural Networks","created":"2022-02-22","cited_by_count":3,"area":null},{"id":"2210.00583","title":"The Dynamic of Consensus in Deep Networks and the Identification of Noisy Labels","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2304.10317","title":"Adaptive Consensus Optimization Method for GANs","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2311.05061","title":"Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2211.09639","title":"Why Deep Learning Generalizes","created":"2022-11-17","cited_by_count":2,"area":null},{"id":"2405.18590","title":"A Margin-based Multiclass Generalization Bound via Geometric Complexity","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2410.08898","title":"Low-Dimension-to-High-Dimension Generalization And Its Implications for Length Generalization","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2503.12211","title":"Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs","created":"2025-03-15","cited_by_count":2,"area":null},{"id":"2510.01930","title":"Precise Dynamics of Diagonal Linear Networks: A Unifying Analysis by Dynamical Mean-Field Theory","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2604.00230","title":"Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2207.12547","title":"The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks","created":"2022-07-25","cited_by_count":1,"area":null},{"id":"2403.01046","title":"A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features","created":"2024-03-02","cited_by_count":1,"area":null},{"id":"2404.07172","title":"A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2405.14111","title":"Improving Generalization of Deep Neural Networks by Optimum Shifting","created":"2024-05-23","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2601.18420","title":"Gradient Regularized Natural Gradients","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.09405","title":"Is Memorization Helpful or Harmful? Prior Information Sets the Threshold","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2103.16355","title":"Nonlinear Weighted Directed Acyclic Graph and A Priori Estimates for Neural Networks","created":"2021-03-30","cited_by_count":0,"area":null},{"id":"2306.13357","title":"Catching Image Retrieval Generalization","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2309.08171","title":"Unveiling Invariances via Neural Network Pruning","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2309.17335","title":"Asynchronous Graph Generator","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2408.02045","title":"DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation","created":"2024-08-04","cited_by_count":0,"area":null},{"id":"2411.16975","title":"ExpTest: Loss-Curve Hypothesis Testing for Autonomous Learning-Rate Selection in Deep Neural Networks","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2506.01350","title":"Variational Adaptive Noise and Dropout towards Stable Recurrent Neural Networks","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2509.16973","title":"Deep Learning Inductive Biases for fMRI Time Series Classification during Resting-state and Movie-watching","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2605.26489","title":"The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.01521","title":"Fast Generalization after Interpolation via Critically Damped Momentum Optimization","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.19368","title":"Neural Architectures as Functional Priors in Physics-Informed Control Problems","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2609.03495","title":"Spectral characteristics of autoencoder parameters as a vector representation of data","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}