Statistical Learning
Hierarchical Graph Representation Learning with Differentiable Pooling
Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, Jure Leskovec
In this framework, we generate deep GNNs by "stacking" GNN
A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization
In particular, ProxSVRG+ generalizes the best results given by the SCSG algorithm, recently proposed by [Lei et al.,
Joint Active Feature Acquisition and Classification with Variable-Size Set Encoding
Hajin Shim, Sung Ju Hwang, Eunho Yang
Neural Information Processing Systems http://nips.cc/
FRAGE: Frequency-Agnostic Word Representation
Chengyue Gong, Di He, Xu Tan, Tao Qin, Liwei Wang, Tie-Yan Liu
FRAGE, we achieve higher performance than the baselines in all tasks.
Connectionist Temporal Classification with Maximum Entropy Regularization
Hu Liu, Sheng Jin, Changshui Zhang
Neural Information Processing Systems http://nips.cc/
End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
Linfeng Zhang, Jiequn Han, Han Wang, Wissam Saidi, Roberto Car, Weinan E
Of particular interest is the inter-atomic potential energy surface (PES).
Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
Mikhail Belkin, Daniel J. Hsu, Partha Mitra
Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong generalization performance for "overfitted" / interpolated classifiers appears to be ubiquitous in high-dimensional data, having been observed in
Dynamic Network Model from Partial Observations
Elahe Ghalebi, Baharan Mirzasoleiman, Radu Grosu, Jure Leskovec
Neural Information Processing Systems http://nips.cc/
Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling
Ridge leverage scores provide a balance between low-rank approximation and regularization, and are ubiquitous in randomized linear algebra and machine learning. Deterministic algorithms are also of interest in the moderately big data regime, because deterministic algorithms provide interpretability to the practitioner by having no failure probability and always returning the same results.
Bayesian Model-Agnostic Meta-Learning
Jaesik Yoon, Taesup Kim, Ousmane Dia, Sungwoong Kim, Yoshua Bengio, Sungjin Ahn
Remaining a gradient-based method, it is also the first Bayesian model-agnostic meta-learning method applicable to various tasks including reinforcement learning.