Theory

A Kernel Theory of Modern Data Augmentation ICML 2019 A large-scale study of the effects of word frequency and predictability in naturalistic reading NAACL 2019 Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees ICLR 2019 Algorithms for Estimating Trends in Global Temperature Volatility AAAI 2019 All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously JMLR 2019 Alternating Minimizations Converge to Second-Order Optimal Solutions ICML 2019 A Max-Affine Spline Perspective of Recurrent Neural Networks ICLR 2019 A Mean Field Theory of Batch Normalization ICLR 2019 A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off NeurIPS 2019 An Abstraction-Based Method for Verifying Strategic Properties in Multi-Agent Systems with Imperfect Information AAAI 2019 A near-optimal algorithm for approximating the John Ellipsoid COLT 2019 An Exponential Efron-Stein Inequality for L_q Stable Learning Rules ALT 2019 An Exponential Tail Bound for the Deleted Estimate AAAI 2019 An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient UAI 2019 A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families NeurIPS 2019 Approximability of Discriminators Implies Diversity in GANs ICLR 2019 Approximate Inference Turns Deep Networks into Gaussian Processes NeurIPS 2019 Approximate Stream Reasoning with Metric Temporal Logic under Uncertainty AAAI 2019 Approximating Integer Solution Counting via Space Quantification for Linear Constraints IJCAI 2019 Approximation and non-parametric estimation of ResNet-type convolutional neural networks ICML 2019 A Principled Approach for Learning Task Similarity in Multitask Learning IJCAI 2019 A Recursive Algorithm for Projected Model Counting AAAI 2019 Are deep ResNets provably better than linear predictors? NeurIPS 2019 A Representer Theorem for Deep Kernel Learning JMLR 2019 A Representer Theorem for Deep Neural Networks JMLR 2019