Permalink
Find file
Fetching contributors…
Cannot retrieve contributors at this time
102 lines (98 sloc) 5.03 KB
@article{amos2016input,
title={Input Convex Neural Networks},
author={Brandon Amos and Lei Xu and J. Zico Kolter},
journal={arXiv preprint arXiv:1609.07152},
_venue={arXiv},
codeurl={https://github.com/locuslab/icnn},
year={2016},
url={http://arxiv.org/abs/1609.07152},
abstract={
This paper presents the input convex neural network
architecture. These are scalar-valued (potentially deep) neural
networks with constraints on the network parameters such that the
output of the network is a convex function of (some of) the
inputs. The networks allow for efficient inference via optimization
over some inputs to the network given others, and can be applied to
settings including structured prediction, data imputation,
reinforcement learning, and others. In this paper we lay the basic
groundwork for these models, proposing methods for inference,
optimization and learning, and analyze their representational
power. We show that many existing neural network architectures can be
made input-convex with only minor modification, and develop
specialized optimization algorithms tailored to this setting. Finally,
we highlight the performance of the methods on multi-label prediction,
image completion, and reinforcement learning problems, where we show
improvement over the existing state of the art in many cases.
}
}
@inproceedings{zhao2016collapsed,
title={{{Collapsed Variational Inference for Sum-Product Networks}}},
author={Han Zhao and Tameem Adel and Geoff Gordon and Brandon Amos},
booktitle={ICML},
_venue={ICML},
year={2016},
url={http://www.cs.cmu.edu/~hzhao1/papers/ICML2016/BL-SPN-main.pdf},
abstract={
Sum-Product Networks (SPNs) are probabilistic inference machines that admit
exact inference in linear time in the size of the network. Existing
parameter learning approaches for SPNs are largely based on the maximum
likelihood principle and hence are subject to overfitting compared to
more Bayesian approaches. Exact Bayesian posterior inference for SPNs is
computationally intractable. Both standard variational inference and
posterior sampling for SPNs are computationally infeasible even for
networks of moderate size due to the large number of local latent
variables per instance. In this work, we propose a novel deterministic
collapsed variational inference algorithm for SPNs that is
computationally efficient, easy to implement and at the same time allows
us to incorporate prior information into the optimization formulation.
Extensive experiments show a significant improvement in accuracy compared
with a maximum likelihood based approach.
}
}
@techreport{amos2016openface,
title={OpenFace: A general-purpose face recognition
library with mobile applications},
author={Amos, Brandon and Bartosz Ludwiczuk and Satyanarayanan, Mahadev},
_venue={CMU},
year={2016},
institution={Technical Report CMU-CS-16-118, CMU School of Computer Science},
url={http://reports-archive.adm.cs.cmu.edu/anon/anon/2016/CMU-CS-16-118.pdf},
codeurl={https://cmusatyalab.github.io/openface},
abstract={
Cameras are becoming ubiquitous in the Internet of Things (IoT) and
can use face recognition technology to improve context. There is a
large accuracy gap between today's publicly available face recognition
systems and the state-of-the-art private face recognition
systems. This paper presents our OpenFace face recognition library
that bridges this accuracy gap. We show that OpenFace provides
near-human accuracy on the LFW benchmark and present a new
classification benchmark for mobile scenarios. This paper is intended
for non-experts interested in using OpenFace and provides a light
introduction to the deep neural network techniques we use.
We released OpenFace in October 2015 as an open source library under
the Apache 2.0 license. It is available at:
<http://cmusatyalab.github.io/openface/>
}
}
@article{amos2014QNSTOP,
title={{{QNSTOP-QuasiNewton Algorithm for Stochastic Optimization}}},
author={Brandon Amos and David Easterling and Layne Watson and
William Thacker and Brent Castle and Michael Trosset},
journal={},
_venue={VT},
year={2014},
keywords={journal},
url={https://vtechworks.lib.vt.edu/bitstream/handle/10919/49672/qnTOMS14.pdf},
abstract={
QNSTOP consists of serial and parallel (OpenMP) Fortran 2003 codes for the
quasi-Newton stochastic optimization method of Castle and Trosset. For
stochastic problems, convergence theory exists for the particular
algorithmic choices and parameter values used in QNSTOP. Both the parallel
driver subroutine, which offers several parallel decomposition strategies,
and the serial driver subroutine can be used for stochastic optimization or
deterministic global optimization, based on an input switch. QNSTOP is
particularly effective for “noisy” deterministic problems, using only
objective function values. Some performance data for computational systems
biology problems is given.
}
}