Generalization

A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks AISTATS 2025 A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities AISTATS 2025 Beyond Accuracy: Revisiting Out-of-Distribution Generalization in NLI Models CoNLL 2025 Critical Influence of Overparameterization on Sharpness-aware Minimization UAI 2025 Do Regularization Methods for Shortcut Mitigation Work As Intended? AISTATS 2025 Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations AISTATS 2025 FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing CVPR 2025 From Sharpness to Better Generalization for Speech Deepfake Detection Interspeech 2025 GCG-Based Artificial Languages for Evaluating Inductive Biases of Neural Language Models CoNLL 2025 Generalization of Graph Neural Networks Is Robust to Model Mismatch AAAI 2025 Improving Generalization of End-to-End ASR through Diversity and Independence Regularization Interspeech 2025 Loss Gradient Gaussian Width based Generalization and Optimization Guarantees AISTATS 2025 Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization UAI 2025 On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent ICLR 2025 Regularity in Canonicalized Models: A Theoretical Perspective AISTATS 2025 Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs AISTATS 2025 Structure based SAT dataset for analysing GNN generalisation AISTATS 2025 The Local Learning Coefficient: A Singularity-Aware Complexity Measure AISTATS 2025 Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context ICLR 2025 Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis ICLR 2025 An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem NeurIPS 2024 Attribute Diversity Determines the Systematicity Gap in VQA EMNLP 2024 ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis ICLR 2024 Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding ICLR 2024 Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise UAI 2024