conftrace_

early stopping

76 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) hyperparameter optimization (406) generalization bound (652) kernel methods (1097) reproducing kernel hilbert space (334) neural network (6616) ensemble learning (1274) stochastic gradient descent (1091) learning rate (192) iterative regularization (8)

Papers

Efficient Hyperparameter Optimization for LLM Reinforcement Learning ACL 2026
S2O: Early Stopping for Sparse Attention via Online Permutation ACL 2026
From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval EMNLP 2025
Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning AAAI 2025
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion ACL 2025
Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling NAACL 2025
Answer Convergence as a Signal for Early Stopping in Reasoning EMNLP 2025
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning EMNLP 2025
High-Dimensional L2-Boosting: Rate of Convergence JMLR 2025
Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent AISTATS 2024
United We Stand: Using Epoch-Wise Agreement of Ensembles to Combat Overfit AAAI 2024
FedES: Federated Early-Stopping for Hindering Memorizing Heterogeneous Label Noise IJCAI 2024
Know When To Stop: A Study of Semantic Drift in Text Generation NAACL 2024
Post-Hoc Reversal: Are We Selecting Models Prematurely? NIPS 2024
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation NIPS 2024
Implicit Regularization of Decentralized Gradient Descent for Sparse Regression NIPS 2024
Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery AAAI 2024
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning JMLR 2023
Operation-Level Early Stopping for Robustifying Differentiable NAS NIPS 2023
Adaptive Textual Label Noise Learning based on Pre-trained Models EMNLP 2023
Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond AISTATS 2023
Calibrating a Deep Neural Network with Its Predecessors IJCAI 2023
Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping ICML 2023
HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption ICML 2023
A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023