Statistical Learning
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting
Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric J. Horvitz, Stefano Ermon
A learned generative model often produces biased statistics relative to the underlying data distribution.
A Universally Optimal Multistage Accelerated Stochastic Gradient Method
Necdet Serhat Aybat, Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar
Neural Information Processing Systems http://nips.cc/
Thinning for Accelerating the Learning of Point Processes
Neural Information Processing Systems http://nips.cc/
Recurrent Kernel Networks
Substring kernels are classical tools for representing biological sequences or text.
Doubly-Robust Lasso Bandit
Neural Information Processing Systems http://nips.cc/
Flexible Modeling of Diversity with Strongly Log-Concave Distributions
Joshua Robinson, Suvrit Sra, Stefanie Jegelka
We develop two fundamental 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
Our methods also generalize naturally to let us prove new convergence bounds on low-precision training with other quantization schemes, such as low-precision floating-point computation and logarithmic quantization.
Co-Generation with GANs using AIS based HMC
Tiantian Fang, Alexander Schwing
Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm.
Manifold-regression to predict from MEG/EEG brain signals without source modeling
David Sabbagh, Pierre Ablin, Gael Varoquaux, Alexandre Gramfort, Denis A. Engemann
However, after artefact-suppression, M/EEG data is often rank deficient which limits the application of Riemannian concepts.