Brandon Amos
Research Scientist
Facebook AI (FAIR)

CV

I am a research scientist at Facebook AI (FAIR) in NYC and broadly study foundational topics and applications in machine learning (sometimes deep) and optimization (sometimes convex), including reinforcement learning, computer vision, language, statistics, and theory. I have a Ph.D. from Carnegie Mellon University and was advised by Zico Kolter and supported by an NSF graduate research fellowship. My thesis is on Differentiable Optimization-Based Modeling for Machine Learning. My publications are available below and on my Google Scholar page and my open source contributions can be found on my Github profile. I have also worked on reinforcement learning during an internship with Nando de Freitas and Misha Denil at DeepMind in 2017 and on vision with Vladlen Koltun at Intel Labs in 2018.

Education

Aug 2014 - May 2019 Ph.D. in Computer Science (0.00/0.00)
Carnegie Mellon University
Aug 2014 - May 2016 M.S. in Computer Science (0.00/0.00)
Carnegie Mellon University
Aug 2011 - May 2014 B.S. in Computer Science (3.99/4.00)
Virginia Tech
Aug 2007 - May 2011 Northside High School (Roanoke, Virginia)

Experience

May 2019 - Present Facebook AI, Research Scientist
June 2018 - Sept 2018 Intel Labs, Research Intern
May 2017 - Oct 2017 Google DeepMind, Research Intern
May 2014 - Aug 2014 Adobe Research, Data Scientist Intern
Dec 2013 - Jan 2014 Snowplow Analytics, Software Engineer Intern
May 2013 - Aug 2013 Qualcomm, Software Engineer Intern
May 2012 - Aug 2012 Phoenix Integration, Software Engineer Intern
Jan 2011 - Aug 2011 Sunapsys, Network Administrator Intern

Selected Publications

Google Scholar

Differentiable Convex Optimization Layers
A. Agrawal*, B. Amos*, S. Barratt*, S. Boyd*, S. Diamond*, and J. Z. Kolter*
NeurIPS 2019
[1] [abs] [pdf] [code]
The Differentiable Cross-Entropy Method
B. Amos and D. Yarats
arXiv 2019
[2] [abs] [pdf]
The Limited Multi-Label Projection Layer
B. Amos, V. Koltun, and J. Z. Kolter
arXiv 2019
[3] [abs] [pdf] [code]
Differentiable Optimization-Based Modeling for Machine Learning
B. Amos
Ph.D. Thesis 2019
[4] [pdf] [code]
Differentiable MPC for End-to-end Planning and Control
B. Amos, I. Rodriguez, J. Sacks, B. Boots, and J. Z. Kolter
NeurIPS 2018
[5] [abs] [pdf] [code]
Depth-Limited Solving for Imperfect-Information Games
N. Brown, T. Sandholm, and B. Amos
NeurIPS 2018
[6] [abs] [pdf]
Learning Awareness Models
B. Amos, L. Dinh, S. Cabi, T. Rothörl, S. Colmenarejo, A. Muldal, T. Erez, Y. Tassa, N. de Freitas, and M. Denil
ICLR 2018
[7] [abs] [pdf]
Task-based End-to-end Model Learning
P. Donti, B. Amos, and J. Z. Kolter
NeurIPS 2017
[8] [abs] [pdf] [code]
OptNet: Differentiable Optimization as a Layer in Neural Networks
B. Amos and J. Z. Kolter
ICML 2017
[9] [abs] [pdf] [code]
Input Convex Neural Networks
B. Amos, L. Xu, and J. Z. Kolter
ICML 2017
[10] [abs] [pdf] [code]
Collapsed Variational Inference for Sum-Product Networks
H. Zhao, T. Adel, G. Gordon, and B. Amos
ICML 2016
[11] [abs] [pdf]
OpenFace: A general-purpose face recognition library with mobile applications
B. Amos, B. Ludwiczuk, and M. Satyanarayanan
CMU 2016
[12] [abs] [pdf] [code]
QNSTOP-QuasiNewton Algorithm for Stochastic Optimization
B. Amos, D. Easterling, L. Watson, W. Thacker, B. Castle, and M. Trosset
VT 2014
[13] [abs] [pdf]

Teaching Experience

S2017 Graduate AI (CMU 15-780), TA
S2016 Distributed Systems (CMU 15-440/640), TA
S2013 Software Design and Data Structures (VT CS 2114), TA

Honors & Awards

2016 - 2019 NSF Graduate Research Fellowship
2011 - 2014 Eight undergraduate scholarships

Service

Reviewer

ICML 2018, NeurIPS 2018, NeurIPS Deep RL Workshop 2018, ICLR 2019 (outstanding reviewer), ICML 2019, ICCV 2019

Admissions

CMU CSD MS 2014-2015

Skills

Languages

C, C++, Fortran, Haskell, Java, Lua, Make, Mathematica, Python, R, Scala

Frameworks

NumPy, Pandas, PyTorch, SciPy, TensorFlow, Torch7

Systems

Linux, OSX

All Publications

Google Scholar

Preprints and Tech Reports

The Differentiable Cross-Entropy Method
B. Amos and D. Yarats
arXiv 2019
[P1] [abs] [pdf]
Generalized Inner Loop Meta-Learning
E. Grefenstette, B. Amos, D. Yarats, P. Htut, A. Molchanov, F. Meier, D. Kiela, K. Cho, and S. Chintala
arXiv 2019
[P2] [abs] [pdf]
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
D. Yarats, A. Zhang, I. Kostrikov, B. Amos, J. Pineau, and R. Fergus
arXiv 2019
[P3] [abs] [pdf]
The Limited Multi-Label Projection Layer
B. Amos, V. Koltun, and J. Z. Kolter
arXiv 2019
[P4] [abs] [pdf] [code]
Differentiable Optimization-Based Modeling for Machine Learning
B. Amos
Ph.D. Thesis 2019
[P5] [pdf] [code]
OpenFace: A general-purpose face recognition library with mobile applications
B. Amos, B. Ludwiczuk, and M. Satyanarayanan
CMU 2016
[P6] [abs] [pdf] [code]
Are Cloudlets Necessary?
Y. Gao, W. Hu, K. Ha, B. Amos, P. Pillai, and M. Satyanarayanan
CMU 2015
[P7] [abs] [pdf]
Adaptive VM handoff across cloudlets
K. Ha, Y. Abe, Z. Chen, W. Hu, B. Amos, P. Pillai, and M. Satyanarayanan
CMU 2015
[P8] [abs] [pdf]
QNSTOP-QuasiNewton Algorithm for Stochastic Optimization
B. Amos, D. Easterling, L. Watson, W. Thacker, B. Castle, and M. Trosset
VT 2014
[P9] [abs] [pdf]

Conference Proceedings

Differentiable Convex Optimization Layers
A. Agrawal*, B. Amos*, S. Barratt*, S. Boyd*, S. Diamond*, and J. Z. Kolter*
NeurIPS 2019
[C1] [abs] [pdf] [code]
Differentiable MPC for End-to-end Planning and Control
B. Amos, I. Rodriguez, J. Sacks, B. Boots, and J. Z. Kolter
NeurIPS 2018
[C2] [abs]
Depth-Limited Solving for Imperfect-Information Games
N. Brown, T. Sandholm, and B. Amos
NeurIPS 2018
[C3] [abs] [pdf]
Learning Awareness Models
B. Amos, L. Dinh, S. Cabi, T. Rothörl, S. Colmenarejo, A. Muldal, T. Erez, Y. Tassa, N. de Freitas, and M. Denil
ICLR 2018
[C4] [abs] [pdf]
A Scalable and Privacy-Aware IoT Service for Live Video Analytics
J. Wang, B. Amos, A. Das, P. Pillai, N. Sadeh, and M. Satyanarayanan
ACM MMSys 2017
Best Paper Award
[C5]
Task-based End-to-end Model Learning
P. Donti, B. Amos, and J. Z. Kolter
NeurIPS 2017
[C6] [abs] [pdf] [code]
OptNet: Differentiable Optimization as a Layer in Neural Networks
B. Amos and J. Z. Kolter
ICML 2017
[C7] [abs] [pdf] [code]
Input Convex Neural Networks
B. Amos, L. Xu, and J. Z. Kolter
ICML 2017
[C8] [abs] [pdf] [code]
Collapsed Variational Inference for Sum-Product Networks
H. Zhao, T. Adel, G. Gordon, and B. Amos
ICML 2016
[C9] [abs] [pdf]

Journal Articles

Quasi-Newton Stochastic Optimization Algorithm for Parameter Estimation of a Stochastic Model of the Budding Yeast Cell Cycle
M. Chen, B. Amos, L. Watson, J. Tyson, Y. Cao, C. Shaffer, M. Trosset, C. Oguz, and G. Kakoti
IEEE/ACM TCBB 2017
[J1]

Workshop, Symposium, and Short Papers

You can teach elephants to dance: agile VM handoff for edge computing
K. Ha, Y. Abe, T. Eiszler, Z. Chen, W. Hu, B. Amos, R. Upadhyaya, P. Pillai, and M. Satyanarayanan
SEC 2017
[W1]
An Empirical Study of Latency in an Emerging Class of Edge Computing Applications for Wearable Cognitive Assistance
Z. Chen, W. Hu, J. Wang, S. Zhao, B. Amos, G. Wu, K. Ha, K. Elgazzar, P. Pillai, R. Klatzky, D. Siewiorek, and M. Satyanarayanan
SEC 2017
[W2]
Quantifying the impact of edge computing on mobile applications
W. Hu, Y. Gao, K. Ha, J. Wang, B. Amos, Z. Chen, P. Pillai, and M. Satyanarayanan
ACM SIGOPS 2016
[W3]
Privacy mediators: helping IoT cross the chasm
N. Davies, N. Taft, M. Satyanarayanan, S. Clinch, and B. Amos
HotMobile 2016
[W4] [abs] [pdf]
Early Implementation Experience with Wearable Cognitive Assistance Applications
Z. Chen, L. Jiang, W. Hu, K. Ha, B. Amos, P. Pillai, A. Hauptmann, and M. Satyanarayanan
WearSys 2015
[W5] [abs] [pdf]
The Case for Offload Shaping
W. Hu, B. Amos, Z. Chen, K. Ha, W. Richter, P. Pillai, B. Gilbert, J. Harkes, and M. Satyanarayanan
HotMobile 2015
[W6] [abs] [pdf]
Performance study of Spindle, a web analytics query engine implemented in Spark
B. Amos and D. Tompkins
CloudCom 2014
[W7] [abs] [pdf] [code]
Global Parameter Estimation for a Eukaryotic Cell Cycle Model in Systems Biology
T. Andrew, B. Amos, D. Easterling, C. Oguz, W. Baumann, J. Tyson, and L. Watson
SummerSim 2014
[W8] [abs] [pdf]
Fortran 95 implementation of QNSTOP for global and stochastic optimization
B. Amos, D. Easterling, L. Watson, B. Castle, M. Trosset, and W. Thacker
SpringSim (HPC) 2014
[W9] [abs] [pdf]
Applying machine learning classifiers to dynamic Android malware detection at scale
B. Amos, H. Turner, and J. White
IWCMC 2013
[W10] [abs] [pdf] [code]

Magazine Articles

Edge Analytics in the Internet of Things
M. Satyanarayanan, P. Simoens, Y. Xiao, P. Pillai, Z. Chen, K. Ha, W. Hu, and B. Amos
IEEE Pervasive Computing 2015
[M1] [abs] [pdf]
Bad Parts: Are Our Manufacturing Systems at Risk of Silent Cyberattacks?
H. Turner, J. White, J. Camelio, C. Williams, B. Amos, and R. Parker
IEEE Security & Privacy 2015
[M2] [abs] [pdf]

Last updated on 2019-10-31