{"list":"other","total":51,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"1605.00251","title":"A vector-contraction inequality for Rademacher complexities","created":"2016-05-01","cited_by_count":142},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"1711.01530","title":"Fisher-Rao Metric, Geometry, and Complexity of Neural Networks","created":"2017-11-05","cited_by_count":100},{"id":"2402.19047","title":"Theoretical Foundations of Deep Selective State-Space Models","created":"2024-02-29","cited_by_count":74},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72},{"id":"1905.03684","title":"Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation","created":"2019-05-09","cited_by_count":71},{"id":"1903.09122","title":"Finite Sample Analysis of Stochastic System Identification","created":"2019-03-21","cited_by_count":67},{"id":"1906.05392","title":"Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian","created":"2019-06-12","cited_by_count":67},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"1902.00768","title":"Learning Linear Dynamical Systems with Semi-Parametric Least Squares","created":"2019-02-02","cited_by_count":58},{"id":"2003.11227","title":"Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems","created":"2020-03-25","cited_by_count":46},{"id":"1910.12947","title":"On Generalization Bounds of a Family of Recurrent Neural Networks","created":"2019-10-28","cited_by_count":42},{"id":"2003.00189","title":"Logarithmic Regret for Adversarial Online Control","created":"2020-02-29","cited_by_count":41},{"id":"2009.00739","title":"Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories","created":"2020-09-01","cited_by_count":38},{"id":"2307.11888","title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","created":"2023-07-21","cited_by_count":36},{"id":"1803.09327","title":"Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization","created":"2018-03-25","cited_by_count":35},{"id":"2304.09856","title":"LipsFormer: Introducing Lipschitz Continuity to Vision Transformers","created":"2023-04-19","cited_by_count":34},{"id":"2310.02980","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors","created":"2023-10-04","cited_by_count":34},{"id":"2206.08269","title":"Learning with little mixing","created":"2022-06-16","cited_by_count":33},{"id":"2311.14495","title":"StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization","created":"2023-11-24","cited_by_count":30},{"id":"2310.13088","title":"Sequence Length Independent Norm-Based Generalization Bounds for Transformers","created":"2023-10-19","cited_by_count":29},{"id":"2202.08311","title":"Single Trajectory Nonparametric Learning of Nonlinear Dynamics","created":"2022-02-16","cited_by_count":26},{"id":"2203.17193","title":"Learning from many trajectories","created":"2022-03-31","cited_by_count":24},{"id":"2310.18780","title":"Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions","created":"2023-10-28","cited_by_count":24},{"id":"2106.01202","title":"Framing RNN as a kernel method: A neural ODE approach","created":"2021-06-02","cited_by_count":23},{"id":"2206.00024","title":"Online PAC-Bayes Learning","created":"2022-05-31","cited_by_count":22},{"id":"2305.06648","title":"Generalization bounds for neural ordinary differential equations and deep residual networks","created":"2023-05-11","cited_by_count":21},{"id":"2405.06147","title":"State-Free Inference of State-Space Models: The Transfer Function Approach","created":"2024-05-10","cited_by_count":18},{"id":"2402.08132","title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","created":"2024-02-12","cited_by_count":17},{"id":"2006.09914","title":"Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes","created":"2020-06-17","cited_by_count":16},{"id":"2208.04284","title":"On Rademacher Complexity-based Generalization Bounds for Deep Learning","created":"2022-08-08","cited_by_count":16},{"id":"1912.03036","title":"Improved PAC-Bayesian Bounds for Linear Regression","created":"2019-12-06","cited_by_count":12},{"id":"2011.09573","title":"Learning Recurrent Neural Net Models of Nonlinear Systems","created":"2020-11-18","cited_by_count":11},{"id":"2405.02670","title":"From Generalization Analysis to Optimization Designs for State Space Models","created":"2024-05-04","cited_by_count":11},{"id":"2402.05928","title":"Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss","created":"2024-02-08","cited_by_count":10},{"id":"2201.11059","title":"Generalization Error Bounds on Deep Learning with Markov Datasets","created":"2021-12-23","cited_by_count":9},{"id":"2401.16655","title":"Rademacher Complexity of Neural ODEs via Chen-Fliess Series","created":"2024-01-30","cited_by_count":5},{"id":"2303.16816","title":"PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss","created":"2023-03-29","cited_by_count":4}],"next_cursor":null}