{"total":30,"rows":[{"id":"2102.04626","title":"Physics-informed neural networks with hard constraints for inverse design","created":"2021-02-09","cited_by_count":280,"area":null},{"id":"2212.07048","title":"PD-Quant: Post-Training Quantization based on Prediction Difference Metric","created":"2022-12-14","cited_by_count":73,"area":null},{"id":"2103.05127","title":"Model Complexity of Deep Learning: A Survey","created":"2021-03-08","cited_by_count":65,"area":null},{"id":"2106.16225","title":"Analytic Insights into Structure and Rank of Neural Network Hessian Maps","created":"2021-06-30","cited_by_count":52,"area":null},{"id":"2102.04877","title":"Noisy Recurrent Neural Networks","created":"2021-02-09","cited_by_count":42,"area":null},{"id":"2102.07346","title":"On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers","created":"2021-02-15","cited_by_count":35,"area":null},{"id":"2103.09985","title":"A deep learning theory for neural networks grounded in physics","created":"2021-03-18","cited_by_count":23,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2107.09133","title":"The Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion","created":"2021-07-19","cited_by_count":19,"area":null},{"id":"2106.14836","title":"Understanding Dynamics of Nonlinear Representation Learning and Its Application","created":"2021-06-28","cited_by_count":11,"area":null},{"id":"2102.10734","title":"Provable Super-Convergence with a Large Cyclical Learning Rate","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2305.09779","title":"A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2104.05785","title":"A Recipe for Global Convergence Guarantee in Deep Neural Networks","created":"2021-04-12","cited_by_count":8,"area":null},{"id":"2309.07110","title":"Data Augmentation via Subgroup Mixup for Improving Fairness","created":"2023-09-13","cited_by_count":8,"area":null},{"id":"2305.01034","title":"Model-agnostic Measure of Generalization Difficulty","created":"2023-05-01","cited_by_count":7,"area":null},{"id":"2504.17160","title":"OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2208.06028","title":"Gaussian Process Surrogate Models for Neural Networks","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2502.17009","title":"Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs","created":"2025-02-24","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":"2301.01352","title":"WLD-Reg: A Data-dependent Within-layer Diversity Regularizer","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2110.01670","title":"A manifold learning approach for gesture recognition from micro-Doppler radar measurements","created":"2021-10-04","cited_by_count":2,"area":null},{"id":"2602.07679","title":"Spectral Gating Networks","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2606.06861","title":"Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2107.13600","title":"To Boost or not to Boost: On the Limits of Boosted Neural Networks","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2207.09225","title":"Similarity of Pre-trained and Fine-tuned Representations","created":"2022-07-19","cited_by_count":0,"area":null},{"id":"2210.13741","title":"Deep Neural Networks as the Semi-classical Limit of Topological Quantum Neural Networks: The problem of generalisation","created":"2022-10-25","cited_by_count":0,"area":null},{"id":"2405.07679","title":"Class-wise Activation Unravelling the Engima of Deep Double Descent","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2412.21149","title":"Functional Risk Minimization","created":"2024-12-30","cited_by_count":0,"area":null},{"id":"2512.18471","title":"The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.24977","title":"SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets","created":"2025-12-31","cited_by_count":0,"area":null}],"next_cursor":null}