Generalization

The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws AISTATS 2025 Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training? CVPR 2025 Training Data Soft Selection via Joint Density Ratio Estimation ACML 2025 Achievable distributional robustness when the robust risk is only partially identified NeurIPS 2024 An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression ICLR 2024 A Systematic Analysis on the Temporal Generalization of Language Models in Social Media ACL 2024 Attribute Diversity Determines the Systematicity Gap in VQA EMNLP 2024 A two-scale Complexity Measure for Deep Learning Models NeurIPS 2024 Bridging the Gap: Rademacher Complexity in Robust and Standard Generalization COLT 2024 Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View. ICLR 2024 CR-SAM: Curvature Regularized Sharpness-Aware Minimization AAAI 2024 Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets NeurIPS 2024 Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression NeurIPS 2024 Generalization and Learnability in Multiple Instance Regression UAI 2024 Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure NeurIPS 2024 Generalization of Hamiltonian algorithms NeurIPS 2024 Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting AAAI 2024 Information-theoretic Generalization Analysis for Expected Calibration Error NeurIPS 2024 Information-theoretic generalization bounds for learning from quantum data COLT 2024 Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification NeurIPS 2024 IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing NeurIPS 2024 Least Squares Regression Can Exhibit Under-Parameterized Double Descent NeurIPS 2024 List Sample Compression and Uniform Convergence COLT 2024 Measuring the Robustness of NLP Models to Domain Shifts EMNLP 2024 Model Collapse Demystified: The Case of Regression NeurIPS 2024