No article text was recorded for this version.
architectural scope limitation (architectural generalization gap)
Version 2 of 2288 papers289 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Generalization Analysis for Deep Contrastive Representation Learning
- Blog: Frequency Bias in Neural Networks for Input of Non-Uniform Density
- Blog: Finite-Time Lyapunov Exponents of Deep Neural Networks
- Blog: A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit
- Blog: A theory of representation learning gives a deep generalisation of kernel methods
- Blog: Mean-field Analysis of Batch Normalization
- Blog: Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
- Blog: On the Generalization Properties of Diffusion Models
- Blog: An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn
- Blog: Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)
- Blog: ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
- Blog: Deep Operator Learning Lessens the Curse of Dimensionality for PDEs
- Blog: Deep Networks and the Multiple Manifold Problem
- Blog: Quantitative CLTs in Deep Neural Networks
- Blog: Depth-induced NTK: Bridging Over-parameterized Neural Networks and Deep Neural Kernels
- Blog: An Information Theoretic Interpretation to Deep Neural Networks
- Blog: Deep Neural Networks as Point Estimates for Deep Gaussian Processes
- Blog: Some Theoretical Insights into Wasserstein GANs
- Blog: Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry
- Blog: Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
- Blog: Generalization Analysis for Deep Contrastive Representation Learning
- Blog: Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity
- Blog: On the Similarity between the Laplace and Neural Tangent Kernels
- Blog: Large-width functional asymptotics for deep Gaussian neural networks
- Blog: BALI: Learning Neural Networks via Bayesian Layerwise Inference
- Blog: A generalization bound of deep neural networks for dependent data
- Blog: Optimization and Generalization Guarantees for Weight Normalization
- Blog: On the Similarity between the Laplace and Neural Tangent Kernels
- Blog: Flexible Infinite-Width Graph Convolutional Neural Networks
- Blog: Minimax Estimation of Neural Net Distance
- Blog: Restricted Strong Convexity of Deep Learning Models with Smooth Activations
- Blog: Deep Neural Networks as Gaussian Processes
- Blog: Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions
- Blog: Constant-Expansion Suffices for Compressed Sensing with Generative Priors
- Blog: Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
- Blog: Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
- Blog: Feature Learning and Signal Propagation in Deep Neural Networks
- Blog: Adaptive Optimization in the ∞-Width Limit
- Blog: Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
- Blog: The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagrams
- Blog: A Kernel Perspective of Skip Connections in Convolutional Networks
- Blog: Adversarial Rademacher Complexity of Deep Neural Networks
- Blog: Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization
- Blog: Adversarial Risk Bounds through Sparsity based Compression
- Blog: Eigen Analysis of Conjugate Kernel and Neural Tangent Kernel
- Blog: Towards a General Theory of Infinite-Width Limits of Neural Classifiers
- Blog: Characterizing the spectrum of the NTK via a power series expansion
- Blog: Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic Explainability
- Blog: The Neural Tangent Link Between CNN Denoisers and Non-Local Filters
- Blog: Stronger Generalization Bounds for Deep Nets via a Compression Approach
- Blog: Feature learning and generalization in deep networks with orthogonal weights
- Blog: Enhanced Recurrent Neural Tangent Kernels for Non-Time-Series Data
- Blog: "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach
- Blog: Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
- Blog: On the interplay of network structure and gradient convergence in deep learning
- Blog: Asymptotics of Ridge Regression in Convolutional Models
- Blog: Information-Theoretic Generalization Bounds for Deep Neural Networks
- Blog: Generalization Bounds for Adversarial Contrastive Learning
- Blog: Improved Sample Complexity Bounds for Diffusion Model Training
- Blog: Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Showing 60 of 288 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_scope_limitation_architect_8872a861,
title = {architectural scope limitation (architectural generalization gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-scope-limitation-architectural-generalization-gap/rdr_8872a8619a544ea689113f31721ae840},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_architectural_scope_limitation_architect_8872a861_v2,
title = {architectural scope limitation (architectural generalization gap)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-scope-limitation-architectural-generalization-gap/rdr_8872a8619a544ea689113f31721ae840/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}