Statistical Learning
Estimating High-dimensional Non-Gaussian Multiple Index Models via Stein’s Lemma
Zhuoran Yang, Krishnakumar Balasubramanian, Zhaoran Wang, Han Liu
Such a model is known as sparse multiple index model (MIM).
Model evidence from nonequilibrium simulations
The marginal likelihood, or model evidence, is a key quantity in Bayesian parameter estimation and model comparison.
Partial Hard Thresholding: Towards A Principled Analysis of Support Recovery
In machine learning and compressed sensing, it is of central importance to understand when a tractable algorithm recovers the support of a sp arse signal from its compressed measurements. In this paper, we present a princi pled analysis on the support recovery performance for a family of hard threshold ing algorithms. To this end, we appeal to the partial hard thresholding (PHT) op erator proposed recently by Jain et al. [IEEE Trans.
Learning to Pivot with Adversarial Networks
Gilles Louppe, Michael Kagan, Kyle Cranmer
Neural Information Processing Systems http://nips.cc/
A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
Steven Cheng-Xian Li, Benjamin M. Marlin
Neural Information Processing Systems http://nips.cc/
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
Hongyi Zhang, Sashank J. Reddi, Suvrit Sra
Neural Information Processing Systems http://nips.cc/
Deep Lattice Networks and Partial Monotonic Functions
Seungil You, David Ding, Kevin Canini, Jan Pfeifer, Maya Gupta
See Figure 1 for an example DLN with nine such layers. Lattices are interpolated look-up tables, as shown in Figure 1.
Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data
Joel A. Tropp, Alp Yurtsever, Madeleine Udell, Volkan Cevher
Here are two important cases where this problem arises.
Accelerating Stochastic Composition Optimization
Mengdi Wang, Ji Liu, Ethan Fang
The popular stochastic gradient methods are well suited for minimizing expected-value objective functions or the sum of a large number of loss functions. Stochastic gradient methods find wide applications in estimation, online learning, and training of deep neural networks.
A Multi-Batch L-BFGS Method for Machine Learning
Albert S. Berahas, Jorge Nocedal, Martin Takac
In order to improve the learning process, we follow a multi-batch approach in which the batch changes at each iteration.