learning theory

Empirical Risk Landscape Analysis for Understanding Deep Neural Networks ICLR 2018 Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions NeurIPS 2018 Generalization Bounds for Uniformly Stable Algorithms NeurIPS 2018 Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks ICML 2018 How Many Samples are Needed to Estimate a Convolutional Neural Network? NeurIPS 2018 Implicit Bias of Gradient Descent on Linear Convolutional Networks NeurIPS 2018 Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization ICML 2018 Learning to Branch ICML 2018 Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes NeurIPS 2018 On how complexity affects the stability of a predictor AISTATS 2018 On Statistical Optimality of Variational Bayes AISTATS 2018 On the Local Minima of the Empirical Risk NeurIPS 2018 Optimal Cooperative Inference AISTATS 2018 Optimal Quantum Sample Complexity of Learning Algorithms JMLR 2018 Quantifying Learning Guarantees for Convex but Inconsistent Surrogates NeurIPS 2018 Query Complexity of Bayesian Private Learning NeurIPS 2018 The Limits of Post-Selection Generalization NeurIPS 2018 Time-Space Tradeoffs for Learning Finite Functions from Random Evaluations, with Applications to Polynomials COLT 2018 Towards a Mathematical Understanding of the Difficulty in Learning With Feedforward Neural Networks CVPR 2018 Understanding Deep Neural Networks with Rectified Linear Units ICLR 2018 What Do Classifiers Actually Learn? a Case Study on Emotion Recognition Datasets Interspeech 2018 A General Characterization of the Statistical Query Complexity COLT 2017 A Learning Theory of Ranking Aggregation AISTATS 2017 An Information-Theoretic Route from Generalization in Expectation to Generalization in Probability AISTATS 2017 Asymptotic Analysis of Objectives Based on Fisher Information in Active Learning JMLR 2017