conftrace_

population loss

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

generalization bound (2) algorithmic stability (2) sample complexity (2) stochastic gradient descent (2) hessian spectrum (1) polyak stepsize (1) natarajan dimension (1) excess empirical loss (1) differentially private algorithm (1) finite-width neural network (1)

Papers

Collaborative Prediction: To Join or To Disjoin Datasets UAI 2025 Learning In-context n-grams with Transformers: Sub-n-grams Are Near-Stationary Points ICML 2025 Rapid Overfitting of Multi-Pass SGD in Stochastic Convex Optimization ICML 2025 The sample complexity of multi-distribution learning COLT 2024 A New Family of Generalization Bounds Using Samplewise Evaluated CMI NeurIPS 2022 From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NeurIPS 2022 Improved Algorithms for Neural Active Learning NeurIPS 2022 Phenomenology of Double Descent in Finite-Width Neural Networks ICLR 2022 Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent AISTATS 2022 Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks NeurIPS 2021 Private Stochastic Convex Optimization with Optimal Rates NeurIPS 2019