← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes CVPR 2025
A Priori Estimation of the Approximation, Optimization and Generalization Errors of Random Neural Networks for Solving Partial Differential Equations IJCAI 2025
Almost Sure Convergence of Dropout Algorithms for Neural Networks JMLR 2025
Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary JMLR 2025
Finite Expression Method for Solving High-Dimensional Partial Differential Equations JMLR 2025
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025
Global Convergence of Adjoint-Optimized Neural PDEs JMLR 2025
O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions JMLR 2025
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025
Contrasting Adversarial Perturbations: The Space of Harmless Perturbations AAAI 2025
DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments AAAI 2025
Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure AAAI 2025
Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025
Length-Induced Embedding Collapse in PLM-based Models ACL 2025
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025
Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs ACL 2025
Statistical inference on black-box generative models in the data kernel perspective space ACL 2025
Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025
Confounding Factors in Relating Model Performance to Morphology EMNLP 2025
Differential Privacy Mechanisms in Neural Tangent Kernel Regression WACV 2025
Not Lost After All: How Cross-Encoder Attribution Challenges Position Bias Assumptions in LLM Summarization EMNLP 2025
DRM Revisited: A Complete Error Analysis JMLR 2025
Equivariant Manifold Neural ODEs and Differential Invariants JMLR 2025
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check EMNLP 2025
Enhancing Implicit Neural Representations via Symmetric Power Transformation AAAI 2025