No article text was recorded for this version.
gated architecture theoretical gap
Version 1 of 138 papers44 conceptsfrozen 2026-10-04
Papers in this version
- Blog: The Recurrent Neural Tangent Kernel
- Blog: Learning and Generalization in RNNs
- Blog: Framing RNN as a kernel method: A neural ODE approach
- Blog: On the Provable Generalization of Recurrent Neural Networks
- Blog: Sample Complexity Bounds for RNNs with Application to Combinatorial Graph Problems (Student Abstract)
- Blog: On Generalization Bounds of a Family of Recurrent Neural Networks
- Blog: Recurrent Neural Networks for Learning Long-term Temporal Dependencies with Reanalysis of Time Scale Representation
- Blog: Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
- Blog: Generalization bounds for non-stationary mixing processes
- Blog: A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics
- Blog: Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics
- Blog: Global optimality of Elman-type RNNs in the mean-field regime
- Blog: State Gradients for RNN Memory Analysis
- Blog: Faster Training of Very Deep Networks Via p-Norm Gates
- Blog: On the Convergence Rate of Training Recurrent Neural Networks
- Blog: Perspectives on learning with recurrent neural networks
- Blog: Verifying Recurrent Neural Networks Using Invariant Inference
- Blog: Recent advances in efficient learning of recurrent networks
- Blog: Learning rule influences recurrent network representations but not attractor structure in decision-making tasks
- Blog: A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
- Blog: Mechanistic Interpretability of RNNs emulating Hidden Markov Models
- Blog: Gradient-free training of recurrent neural networks using random perturbations
- Blog: On Efficiently Representing Regular Languages as RNNs
- Blog: Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods
- Blog: Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries
- Blog: Neural Tangents: Fast and Easy Infinite Neural Networks in Python
- Blog: Can SGD Learn Recurrent Neural Networks with Provable Generalization?
- Blog: On Multiplicative Integration with Recurrent Neural Networks
- Blog: DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs
- Blog: Information dynamics and Memory in Neural Networks through Fisher Information Diffusion
- Blog: Expressive power of recurrent neural networks
- Blog: Approximating Real-Time Recurrent Learning with Random Kronecker Factors
- Blog: Length independent PAC-Bayes bounds for Simple RNNs
- Blog: Learning in Gated Neural Networks
- Blog: Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
- Blog: ADMMiRNN: Training RNN with Stable Convergence via An Efficient ADMM Approach
- Blog: Persistent RNNs: Stashing Recurrent Weights On-Chip
- Blog: iNNvestigate neural networks!
History & citation
Current · Permanent link
- This direction split from The Mathematical Theory of Gated Recurrence (79% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_gated_architecture_theoretical_gap_cffa7f58,
title = {gated architecture theoretical gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gated-architecture-theoretical-gap/rdr_cffa7f58d07b4bb89304bb43d9739907},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_gated_architecture_theoretical_gap_cffa7f58_v1,
title = {gated architecture theoretical gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/gated-architecture-theoretical-gap/rdr_cffa7f58d07b4bb89304bb43d9739907/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}