Author name cluster

Andrew Miller

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

CLeaR Conference 2022 Conference Paper

Learning Invariant Representations with Missing Data

Mark Goldstein
Joern-Henrik Jacobsen
Olina Chau
Adriel Saporta
Aahlad Manas Puli
Rajesh Ranganath
Andrew Miller

Spurious correlations, or *shortcuts*, allow flexible models to predict well during training but poorly on related test populations. Recent work has shown that models that satisfy particular independencies involving the correlation-inducing *nuisance* variable have guarantees on their test performance. However, enforcing such independencies requires nuisances to be observed during training. But nuisances such as demographics or image background labels are often missing. Enforcing independence on just the observed data does not imply independence on the entire population. In this work, we derive the missing-mmd estimator used for invariance objectives under missing nuisances. On simulations and clinical data, missing-mmds enable improvements in test performance similar to those achieved by using fully-observed data.

PDF Details

NeurIPS Conference 2017 Conference Paper

Reducing Reparameterization Gradient Variance

Andrew Miller
Nick Foti
Alexander D'Amour
Ryan Adams

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the ``reparameterization trick, '' represent a class of noisy gradients often used in Monte Carlo variational inference (MCVI). However, when these gradient estimators are too noisy, the optimization procedure can be slow or fail to converge. One way to reduce noise is to generate more samples for the gradient estimate, but this can be computationally expensive. Instead, we view the noisy gradient as a random variable, and form an inexpensive approximation of the generating procedure for the gradient sample. This approximation has high correlation with the noisy gradient by construction, making it a useful control variate for variance reduction. We demonstrate our approach on a non-conjugate hierarchical model and a Bayesian neural net where our method attained orders of magnitude (20-2{, }000$\times$) reduction in gradient variance resulting in faster and more stable optimization.

PDF Details

NeurIPS Conference 2015 Conference Paper

A Gaussian Process Model of Quasar Spectral Energy Distributions

Andrew Miller
Albert Wu
Jeff Regier
Jon McAuliffe
Dustin Lang
Mr. Prabhat
David Schlegel
Ryan Adams

We propose a method for combining two sources of astronomical data, spectroscopy and photometry, that carry information about sources of light (e. g. , stars, galaxies, and quasars) at extremely different spectral resolutions. Our model treats the spectral energy distribution (SED) of the radiation from a source as a latent variable that jointly explains both photometric and spectroscopic observations. We place a flexible, nonparametric prior over the SED of a light source that admits a physically interpretable decomposition, and allows us to tractably perform inference. We use our model to predict the distribution of the redshift of a quasar from five-band (low spectral resolution) photometric data, the so called ``photo-z'' problem. Our method shows that tools from machine learning and Bayesian statistics allow us to leverage multiple resolutions of information to make accurate predictions with well-characterized uncertainties.

PDF Details

ICRA Conference 2008 Conference Paper

Landing a UAV on a runway using image registration

Andrew Miller
Mubarak Shah
Don Harper

In this paper we present a system that uses only vision to land a UAV on a runway. We describe a method for estimating the relative location of the runway as an image by performing image registration against a stack of images in which the location of the runway is known. An approximation of the camera projection model for a forward-facing view of a runway is derived, allowing the course deviation of the UAV to be estimated from a registered image. The course deviation is used as input to a linear feedback control loop to maintain the correct flight path. Our method is implemented as a real-time multithreaded application, which is used to control an aircraft in Microsoft Flight Simulator. We also show results of applying the vision component of the system to video recorded from an actual UAV.

Details

AAAI Conference 2007 Conference Paper

A Vision-Based System for a UGV to Handle a Road Intersection

Javed Ahmed
Andrew Miller

We propose a real-time computer vision system that enables a UGV to safely cross urban road-intersections. Speciﬁcally, when the UGV approaches the stop sign at a 4-way intersection, it must be aware of the vehicles at the other three roads and adhere to trafﬁc rules by waiting for its turn to proceed. The proposed solution consists of three main components: a vehicle detector, a tracker, and a ﬁnite-state-machine to model the trafﬁc. We use an OT-MACH ﬁlter to detect the leading vehicle in each of three camera-views of the corresponding roads. Then, we track the vehicles using an edge-enhanced dynamic correlation tracker, which estimates the current and next positions, velocities, and accelerations of the vehicles. Finally, the ﬁnite-state-machine describes the trafﬁc in each road with one of four possible states (i. e. No Vehicle Waiting, Arriving, Waiting, and Passing), and signals an autopilot system when it is safe to pass the intersection. We provide the results from an actual intersection with real trafﬁc to demonstrate that the UGV is able to automatically navigate the intersection using the proposed system.

PDF Details