algorithmic stability

Algorithmic Stability Based Generalization Bounds for Adversarial Training ICLR 2025 Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games ICML 2025 Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent AAAI 2025 Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability AISTATS 2025 Leave-One-Out Stable Conformal Prediction ICLR 2025 Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods ICLR 2025 Stability and Generalization for Stochastic (Compositional) Optimizations IJCAI 2025 Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses ICML 2024 Building a stable classifier with the inflated argmax NeurIPS 2024 Credit Attribution and Stable Compression NeurIPS 2024 Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization IJCAI 2024 Generalization and Stability of Interpolating Neural Networks with Minimal Width JMLR 2024 Generalization Bounds for Label Noise Stochastic Gradient Descent AISTATS 2024 Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm ICML 2024 On Statistical Learning Theory for Distributional Inputs ICML 2024 On the Computational Landscape of Replicable Learning NeurIPS 2024 Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance JMLR 2024 Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters AISTATS 2024 Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions ICML 2023 Algorithmic Stability of Heavy-Tailed Stochastic Gradient Descent on Least Squares ALT 2023 Average Sensitivity of Decision Tree Learning ICLR 2023 Exponential Generalization Bounds with Near-Optimal Rates for L_q-Stable Algorithms ICLR 2023 Fast Convergence in Learning Two-Layer Neural Networks with Separable Data AAAI 2023 Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy AISTATS 2023 Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic Stability ICML 2023