Statistical Learning

Variance Reduced Policy Evaluation with Smooth Function Approximation NeurIPS 2019 VC Classes are Adversarially Robustly Learnable, but Only Improperly COLT 2019 Vocal Biomarker Assessment Following Pediatric Traumatic Brain Injury: A Retrospective Cohort Study Interspeech 2019 V-to-V Coarticulation Induced Acoustic and Articulatory Variability of Vowels: The Effect of Pitch-Accent Interspeech 2019 Weak Detection of Signal in the Spiked Wigner Model ICML 2019 What is the Effect of Importance Weighting in Deep Learning? ICML 2019 What Kind of Language Is Hard to Language-Model? ACL 2019 When can unlabeled data improve the learning rate? COLT 2019 Zooming in on Spatiotemporal V-to-C Coarticulation with Functional PCA Interspeech 2019 Accelerating Cross-Validation in Multinomial Logistic Regression with ℓ_1-Regularization JMLR 2018 Accurate Inference for Adaptive Linear Models ICML 2018 Accurate Uncertainties for Deep Learning Using Calibrated Regression ICML 2018 A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models ICML 2018 Analyzing Correlated Evolution of Multiple Features Using Latent Representations EMNLP 2018 Analyzing Reaction Time Sequences from Human Participants in Auditory Experiments Interspeech 2018 An Efficient and Provable Approach for Mixture Proportion Estimation Using Linear Independence Assumption CVPR 2018 An Estimation and Analysis Framework for the Rasch Model ICML 2018 A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks ICLR 2018 Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions ICML 2018 A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization ICML 2018 A Probability Weighted Beamformer for Noise Robust ASR Interspeech 2018 Assessing Generative Models via Precision and Recall NeurIPS 2018 Automatic Metric Validation for Grammatical Error Correction ACL 2018 Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization JMLR 2018 Backpropagation through the Void: Optimizing control variates for black-box gradient estimation ICLR 2018