← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

P2 Law: Scaling Law for Post-Training After Model Pruning ACL 2025
Circuit Stability Characterizes Language Model Generalization ACL 2025
Decoding Knowledge Attribution in Mixture-of-Experts: A Framework of Basic-Refinement Collaboration and Efficiency Analysis ACL 2025
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory ACL 2025
Contrasting Adversarial Perturbations: The Space of Harmless Perturbations AAAI 2025
Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure AAAI 2025
Predicting Fine-tuned Performance on Larger Datasets Before Creating Them COLING 2025
DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments AAAI 2025
Finite Expression Method for Solving High-Dimensional Partial Differential Equations JMLR 2025
Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025
On the Hardness of Training Deep Neural Networks Discretely AAAI 2025
Scaling Laws for Multilingual Language Models ACL 2025
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes CVPR 2025
Extracting and Understanding the Superficial Knowledge in Alignment NAACL 2025
Activation Subspaces for Out-of-Distribution Detection ICCV 2025
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning ACL 2025
Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey ACL 2025
Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs ACL 2025
Monitoring Primitive Interactions During the Training of DNNs AAAI 2025
Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary JMLR 2025
Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention ICCV 2025
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025
The First Theoretical Approximation Guarantees for the Non-Dominated Sorting Genetic Algorithm III (NSGA-III) IJCAI 2025
A Priori Estimation of the Approximation, Optimization and Generalization Errors of Random Neural Networks for Solving Partial Differential Equations IJCAI 2025
Towards Understanding How Knowledge Evolves in Large Vision-Language Models CVPR 2025