overfitting

Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations ICML 2025 Aggregation Buffer: Revisiting DropEdge with a New Parameter Block ICML 2025 Approximately Correct Label Distribution Learning ICML 2025 ARS: Adaptive Reward Scaling for Multi-Task Reinforcement Learning ICML 2025 A Theoretical Framework For Overfitting In Energy-based Modeling ICML 2025 Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning ICML 2025 Boosting Adversarial Robustness with CLAT: Criticality Leveraged Adversarial Training ICML 2025 Enhancing Target-unspecific Tasks through a Features Matrix ICML 2025 EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification ICML 2025 Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective ICML 2025 Federated Learning for Feature Generalization with Convex Constraints ICML 2025 GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras ICML 2025 Grokking Beyond the Euclidean Norm of Model Parameters ICML 2025 How Much Can We Forget about Data Contamination? ICML 2025 Implicit degree bias in the link prediction task ICML 2025 Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection ICML 2025 Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks ICML 2025 Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification COLT 2025 Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization ICML 2025 Rethinking Benign Overfitting in Two-Layer Neural Networks ICML 2025 Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection ICML 2025 Augmented Neural Fine-tuning for Efficient Backdoor Purification ECCV 2024 BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation ICML 2024 Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum ICML 2024 Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings ICML 2024