Statistical Learning
730ce0ae730f39e4d77b0f04a8afe4be-Supplemental-Conference.pdf
This paper studies the use of a machine learning-based estimator as a control variate for mitigating the variance of Monte Carlo sampling. Specifically, we seek to uncover the key factors that influence the efficiency of control variates in reducing variance.
Flexible Modeling of Diversity with Strongly Log-Concave Distributions
Joshua Robinson, Suvrit Sra, Stefanie Jegelka
Wedevelop twofundamental tools needed to apply SLC distributions to learning and inference:sampling and mode finding. For sampling we develop an MCMC sampler and give theoretical mixing time bounds.
Dimension-Free Bounds for Low-Precision Training
Zheng Li, Christopher M. De Sa
Neural Information Processing Systems http://nips.cc/
Binary Classification from Positive-Confidence Data
Takashi Ishida, Gang Niu, Masashi Sugiyama
Neural Information Processing Systems http://nips.cc/
Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning
We conducted the experiment on Meta-World, a multi-task RL benchmark containing various robotics manipulation tasks.
Manifold-regression to predict from MEG/EEG brain signals without source modeling
David Sabbagh, Pierre Ablin, Gael Varoquaux, Alexandre Gramfort, Denis A. Engemann
The Wasserstein distance readily applies to rank-reduced databutlacksaffine-invariance.
Learning Disentangled Representation for Robust Person Re-identification
Neural Information Processing Systems http://nips.cc/