No article text was recorded for this version.
existence-trainability gap
Version 1 of 144 papers48 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Deep neural network approximations for solutions of PDEs based on Monte Carlo algorithms
- Blog: Space-time error estimates for deep neural network approximations for differential equations
- Blog: Quantitative Universal Approximation Bounds for Deep Belief Networks
- Blog: MaskAAE: Latent space optimization for Adversarial Auto-Encoders
- Blog: How Many Neurons Does it Take to Approximate the Maximum?
- Blog: Deep Neural Network Approximation Theory
- Blog: Theoretical guarantees for sampling and inference in generative models with latent diffusions
- Blog: Non-asymptotic Performance Guarantees for Neural Estimation of f-Divergences
- Blog: On the loss landscape of a class of deep neural networks with no bad local valleys
- Blog: On the Existence of Optimal Shallow Feedforward Networks with ReLU Activation
- Blog: Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
- Blog: An Information-Theoretic Analysis of In-Context Learning
- Blog: When Does Optimizing a Proper Loss Yield Calibration?
- Blog: Universality of Deep Convolutional Neural Networks
- Blog: On the stable recovery of deep structured linear networks under sparsity constraints
- Blog: A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- Blog: On the existence of minimizers in shallow residual ReLU neural network optimization landscapes
- Blog: Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data
- Blog: Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities
- Blog: When Does Optimizing a Proper Loss Yield Calibration?
- Blog: Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions
- Blog: Approximation and non-parametric estimation of ResNet-type convolutional neural networks
- Blog: Characterizing ResNet's Universal Approximation Capability
- Blog: Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks
- Blog: Size-Noise Tradeoffs in Generative Networks
- Blog: How to Choose an Activation Function
- Blog: Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds
- Blog: Universal approximation power of deep residual neural networks via nonlinear control theory
- Blog: On the Expressive Power of Permutation-Equivariant Weight-Space Networks
- Blog: Towards Provable Emergence of In-Context Reinforcement Learning
- Blog: An Information-theoretic Approach to Distribution Shifts
- Blog: A Theory for Compressibility of Graph Transformers for Transductive Learning
- Blog: DNN Expression Rate Analysis of High-Dimensional PDEs: Application to Option Pricing
- Blog: ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate
- Blog: Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input
- Blog: Training deep residual networks for uniform approximation guarantees
- Blog: Understanding Sharpness Dynamics in NN Training with a Minimalist Example: The Effects of Dataset Difficulty, Depth, Stochasticity, and More
- Blog: Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies
- Blog: The Kolmogorov–Arnold representation theorem revisited
- Blog: Memorization Capacity for Additive Fine-Tuning with Small ReLU Networks
- Blog: Approximations with deep neural networks in Sobolev time-space
- Blog: Smooth function approximation by deep neural networks with general activation functions
- Blog: Universal Approximation with Certified Networks
- Blog: Approximation Rates for Deep Calibration of (Rough) Stochastic Volatility Models
History & citation
Current · Permanent link
- This direction split from The Reachability of Theoretically Optimal Neural Networks (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_existence_trainability_gap_106a252e,
title = {existence-trainability gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/existence-trainability-gap/rdr_106a252eb469432890492380e966621b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_existence_trainability_gap_106a252e_v1,
title = {existence-trainability gap},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/existence-trainability-gap/rdr_106a252eb469432890492380e966621b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}