Statistical Learning
Mixtape: Breaking the Softmax Bottleneck Efficiently
Zhilin Yang, Thang Luong, Russ R. Salakhutdinov, Quoc V. Le
Neural Information Processing Systems http://nips.cc/
Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
Conghui Tan, Tong Zhang, Shiqian Ma, Ji Liu
Regularized empirical risk minimization problem with linear predictor appears frequentlyinmachinelearning.
AUnifiedConvergenceTheoremforStochastic OptimizationMethods
In this work, we provide a fundamental unified convergence theorem used for deriving expected and almost sure convergence results for a series of stochastic optimization methods.
Conformalized Quantile Regression
Yaniv Romano, Evan Patterson, Emmanuel Candes
Conformal prediction is atechnique for constructing prediction intervals that attainvalidcoverage infinite samples, without making distributional assumptions. Despite this appeal, existing conformal methods can be unnecessarily conservativebecause theyform intervals ofconstant orweakly varying length across the input space.
NAOMI: Non-Autoregressive Multiresolution Sequence Imputation
Yukai Liu, Rose Yu, Stephan Zheng, Eric Zhan, Yisong Yue
Neural Information Processing Systems http://nips.cc/
Query K-means Clustering and the Double Dixie Cup Problem
I Chien, Chao Pan, Olgica Milenkovic
Neural Information Processing Systems http://nips.cc/
Understanding Sparse JL for Feature Hashing
Neural Information Processing Systems http://nips.cc/