← 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

Refined bounds for algorithm configuration: The knife-edge of dual class approximability ICML 2020
Minimizing Dynamic Regret and Adaptive Regret Simultaneously AISTATS 2020
k-means++: few more steps yield constant approximation ICML 2020
Optimal multiclass overfitting by sequence reconstruction from Hamming queries ALT 2020
Near-Optimal SQ Lower Bounds for Agnostically Learning Halfspaces and ReLUs under Gaussian Marginals NIPS 2020
Margins are Insufficient for Explaining Gradient Boosting NIPS 2020
On Performance Estimation in Automatic Algorithm Configuration AAAI 2020
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NIPS 2020
A Closer Look at the Training Strategy for Modern Meta-Learning NIPS 2020
Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle ICML 2020
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent ICML 2020
On Convergence and Generalization of Dropout Training NIPS 2020
Learning Parities with Neural Networks NIPS 2020
On the universality of deep learning NIPS 2020
Teaching with Limited Information on the Learner’s Behaviour ICML 2020
Kernel Alignment Risk Estimator: Risk Prediction from Training Data NIPS 2020
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes NIPS 2019
A Generalization Bound for Online Variational Inference ACML 2019
Nearly-tight VC-dimension and Pseudodimension Bounds for Piecewise Linear Neural Networks JMLR 2019
Optimality Implies Kernel Sum Classifiers are Statistically Efficient ICML 2019
The information-theoretic value of unlabeled data in semi-supervised learning ICML 2019
On Learning Invariant Representations for Domain Adaptation ICML 2019
The advantages of multiple classes for reducing overfitting from test set reuse ICML 2019
Learning and Inference for Structured Prediction: A Unifying Perspective IJCAI 2019
Hypothesis Set Stability and Generalization NIPS 2019