← Keywords

learning theory

518 papers

Explore in graph

Co-occurring keywords

generalization bound (649) sample complexity (1158) statistical learning (350) neural network (6616) online learning (1770) gradient descent (1143) stochastic gradient descent (1088) empirical risk minimization (348) convergence rate (606) pac learning (280)

Papers

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NIPS 2023
Benign Overfitting of Constant-Stepsize SGD for Linear Regression JMLR 2023
Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity NIPS 2023
A universally consistent learning rule with a universally monotone error JMLR 2022
A spectral-based analysis of the separation between two-layer neural networks and linear methods JMLR 2022
KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints JMLR 2022
Identifiability Conditions for Domain Adaptation ICML 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime NIPS 2022
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022
On Robust Multiclass Learnability NIPS 2022
Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and the Explanations AAAI 2022
Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts NIPS 2022
On Leave-One-Out Conditional Mutual Information For Generalization NIPS 2022
Generalization Bounds for Gradient Methods via Discrete and Continuous Prior NIPS 2022
When Hardness of Approximation Meets Hardness of Learning JMLR 2022
Towards Bridging Sample Complexity and Model Capacity AAAI 2022
On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model NIPS 2022
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks NIPS 2022
Exact Learning of Preference Structure: Single-peaked Preferences and Beyond ICML 2022
On Numerical Integration in Neural Ordinary Differential Equations ICML 2022
Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise COLT 2022
Overparameterization from Computational Constraints NIPS 2022
Hardness of Learning a Single Neuron with Adversarial Label Noise AISTATS 2022
On the Statistical Benefits of Curriculum Learning ICML 2022
On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games ICML 2022