Statistical Learning
Fully Understanding The Hashing Trick
Casper B. Freksen, Lior Kamma, Kasper Green Larsen
Feature hashing, also known as the hashing trick, introduced by Weinberger et al. (2009), is one of the key techniques used in scaling-up machine learning algorithms.
NAIS-Net: Stable Deep Networks from Non-Autonomous Differential Equations
Marco Ciccone, Marco Gallieri, Jonathan Masci, Christian Osendorfer, Faustino Gomez
Recently, several researchers have started to view VDNNs from a dynamical systems perspective.
Bayesian Model Selection Approach to Boundary Detection with Non-Local Priors
Fei Jiang, Guosheng Yin, Francesca Dominici
Based on non-local prior distributions, we propose a Bayesian model selection (BMS) procedure for boundary detection in a sequence of data with multiple systematic mean changes. The BMS method can effectively suppress the non-boundary spike points with large instantaneous changes.
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
Md Enayat Ullah, Poorya Mianjy, Teodor Vanislavov Marinov, Raman Arora
Neural Information Processing Systems http://nips.cc/
Distributionally Robust Graphical Models
Rizal Fathony, Ashkan Rezaei, Mohammad Ali Bashiri, Xinhua Zhang, Brian Ziebart
Neural Information Processing Systems http://nips.cc/
Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation
Chaitanya Ryali, Gautam Reddy, Angela J. Yu
It has been found that DBM captures human behavior better than FBM, even though the latter more veridically captures experimental design in a variety of tasks, e.g.
Evolved Policy Gradients
Rein Houthooft, Yuhua Chen, Phillip Isola, Bradly Stadie, Filip Wolski, OpenAI Jonathan Ho, Pieter Abbeel
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.
Revisiting $(\epsilon, \gamma, \tau)$-similarity learning for domain adaptation
The author was at CREATIS when this work was done.
Discretely Relaxing Continuous Variables for tractable Variational Inference
This is unfortunate since the safety afforded by Bayesian statistics is extremely valuable in many prominent mobile applications. For example, the cost of erroneous decisions are very high in autonomous driving or mobile robotic control.
Variational Bayesian Monte Carlo
We introduce here a novel sample-efficient inference framework, V ariational Bayesian Monte Carlo (VBMC). VBMC combines variational inference with Gaussian-process based, active-sampling Bayesian quadrature, using the latter to efficiently approximate the intractable integral in the variational objective.