← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity AISTATS 2024
Wide Two-Layer Networks can Learn from Adversarial Perturbations NIPS 2024
A Canonicalization Perspective on Invariant and Equivariant Learning NIPS 2024
Neural Conditional Probability for Uncertainty Quantification NIPS 2024
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024
Robust Image Denoising through Adversarial Frequency Mixup CVPR 2024
Epistemic Uncertainty Quantification For Pre-Trained Neural Networks CVPR 2024
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation CVPR 2024
Length independent PAC-Bayes bounds for Simple RNNs AISTATS 2024
SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification AISTATS 2024
An Empirical Study of Scaling Law for Scene Text Recognition CVPR 2024
SMR: State Memory Replay for Long Sequence Modeling ACL 2024
Why are Sensitive Functions Hard for Transformers? ACL 2024
Learned Transformer Position Embeddings Have a Low-Dimensional Structure ACL 2024
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures AISTATS 2024
HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position ACL 2024
Improved Sample Complexity Bounds for Diffusion Model Training NIPS 2024
Spectrum Extraction and Clipping for Implicitly Linear Layers AISTATS 2024
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees NIPS 2024
Unveiling Linguistic Regions in Large Language Models ACL 2024
Globally Convergent Variational Inference NIPS 2024
SVDinsTN: A Tensor Network Paradigm for Efficient Structure Search from Regularized Modeling Perspective CVPR 2024
A two-scale Complexity Measure for Deep Learning Models NIPS 2024
Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training CVPR 2024
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning NIPS 2024