generalization performance
Generalization performance refers to a model’s ability to perform well on unseen data drawn from the same distribution as the training data. It’s a critical measure of a model’s effectiveness and robustness in real-world scenarios.
- Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization
- Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation
- Epistemic Uncertainty for Generated Image Detection
- Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline
- FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
- Generalization Bounds for Model-based Algorithm Configuration
- Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming
- Generalization vs Specialization under Concept Shift
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
- HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
- How Memory in Optimization Algorithms Implicitly Modifies the Loss
- Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis
- Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
- Pay Attention to Small Weights
- Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability
- Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
- Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
- Solving Partial Differential Equations via Radon Neural Operator
- TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses
- The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
- Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning
- Tight High-Probability Bounds for Nonconvex Heavy-Tailed Scenario under Weaker Assumptions
- ToolRL: Reward is All Tool Learning Needs
- Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
- Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks