Statistical Learning
Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets
Neural Information Processing Systems http://nips.cc/
Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node
Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, Rohan Kadekodi
This makes them expensive and limits the size of the dataset.
Learning with Incremental Iterative Regularization
Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prove strong universal consistency, i.e. almost sure convergence of the risk, as well as sharp finite sample bounds for the iterates. Our results are a step towards understanding the effect of multiple epochs in stochastic gradient techniques in machine learning and rely on integrating statistical and optimization results.
Efficient Non-greedy Optimization of Decision Trees
Mohammad Norouzi, Maxwell Collins, Matthew A. Johnson, David J. Fleet, Pushmeet Kohli
Decision trees and randomized forests are widely used in computer vision and machine learning.
Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem
DongDong Ge, Haoyue Wang, Zikai Xiong, Yinyu Ye
Different from regularization approaches, our method achieves a well-balanced tradeoff between accuracy and speed. A numerical comparison on various distributions with existing algorithms exhibits the computational advantages of our approach.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun
Neural Information Processing Systems http://nips.cc/
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems
Finally, we prove that the algorithm's
Semi-Parametric Efficient Policy Learning with Continuous Actions
Victor Chernozhukov, Mert Demirer, Greg Lewis, Vasilis Syrgkanis
Neural Information Processing Systems http://nips.cc/