I am a researcher 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 am finishing a Ph.D. at Carnegie Mellon University advised by Zico Kolter and am supported by an NSF graduate research fellowship. My dissertation is entitled “Differentiable Optimization-Based Inference for Machine Learning” and my thesis proposal is available here. My publications are available below and on my Google Scholar page.

My research straddles applied and theoretical contributions. Over the past three years (since 2016) I have focused on foundational contributions to the NeurIPS, ICML, and ICLR communities. The core pillars of my dissertation are my ICML 2017 papers on input-convex neural networks and OptNet layers. My NeurIPS 2018 paper uses OptNet as a foundation to combine model-free and model-based reinforcement learning. I have also worked on reinforcement learning during an internship with Nando de Freitas and Misha Denil at DeepMind in 2017, publishing an ICLR 2018 paper Learning Awareness Models, and on combinatorial and discrete learning problems with Vladlen Koltun at Intel Labs in 2018.

Before this, as an undergraduate (from 2011-2014) I focused on compilers, distributed systems, mobile computing, and Quasi-Newton Methods for Stochastic Optimization. I value important societal applications of my work and spent the first two years of my Ph.D. (from 2014-2016) working on applied machine learning and computer vision technologies underlying mobile and wearable cognitive assistance systems with Mahadev Satyanarayanan, publishing papers at systems- and mobile-oriented venues during this time.

I strongly believe in open science, reproducible research, and well-engineered projects and actively publish code on my Github profile. This led me to create OpenFace in 2016.

Education

Aug 2014 - May 2019 (expected) Ph.D. in Computer Science
Carnegie Mellon University
Aug 2014 - May 2016 M.S. in Computer Science
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)

Research Experience

Apr 2016 - Present Carnegie Mellon University, Zico Kolter
Machine learning and optimization
June 2018 - Sept 2018 Intel Labs, Vladlen Koltun
Machine learning
May 2017 - Oct 2017 Google DeepMind, Nando de Freitas
Machine and reinforcement learning
Aug 2014 - Apr 2016 Carnegie Mellon University, Mahadev Satyanarayanan
Applied machine learning and mobile systems
May 2012 - May 2014 Virginia Tech, Jules White
Mobile systems, cyber-physical systems, and security
Jan 2013 - May 2014 Virginia Tech, Layne Watson
Scientific computing, global/stochastic optimization, and bioinformatics
Nov 2012 - Mar 2014 Virginia Tech, Binoy Ravindran
Heterogeneous compilers

Selected Publications

Google Scholar

Differentiable MPC for End-to-end Planning and Control
B. Amos, I. Rodriguez, J. Sacks, B. Boots, and J. Kolter
NeurIPS 2018
[1] [abs] [pdf] [code]
Depth-Limited Solving for Imperfect-Information Games
N. Brown, T. Sandholm, and B. Amos
NeurIPS 2018
[2] [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
[3] [abs] [pdf]
Task-based End-to-end Model Learning
P. Donti, B. Amos, and J. Kolter
NeurIPS 2017
[4] [abs] [pdf] [code]
OptNet: Differentiable Optimization as a Layer in Neural Networks
B. Amos and J. Kolter
ICML 2017
[5] [abs] [pdf] [code]
Input Convex Neural Networks
B. Amos, L. Xu, and J. Kolter
ICML 2017
[6] [abs] [pdf] [code]
Collapsed Variational Inference for Sum-Product Networks
H. Zhao, T. Adel, G. Gordon, and B. Amos
ICML 2016
[7] [abs] [pdf]
OpenFace: A general-purpose face recognition library with mobile applications
B. Amos, B. Ludwiczuk, and M. Satyanarayanan
CMU 2016
[8] [abs] [pdf] [code]
QNSTOP-QuasiNewton Algorithm for Stochastic Optimization
B. Amos, D. Easterling, L. Watson, W. Thacker, B. Castle, and M. Trosset
VT 2014
[9] [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

Industry Experience

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

CMU Graduate Coursework

  • Statistical Machine Learning (10-702, Au), L. Wasserman, S2017
  • Deep Reinforcement Learning (10-703, Au), R. Salakhutdinov and A. Fragkiadaki, S2017
  • Intermediate Statistics (10-705, Au), L. Wasserman, F2016
  • Topics in Deep Learning (10-807), R. Salakhutdinov, F2016
  • Convex Optimization (10-725), R. J. Tibshirani, F2015
  • Algorithms in the Real World (15-853), G. Blelloch and A. Gupta, F2015
  • Semantics of Programming Languages (15-812), A. Platzer, S2015
  • Optimizing Compilers for Modern Architecture (15-745), T. Mowry, S2015
  • Advanced Operating and Distributed Systems (15-712), D. Andersen, F2014
  • Mobile and Pervasive Computing (15-812), M. Satyanarayanan and D. Siewiorek, F2014

Honors & Awards

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

Skills

Languages

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

Frameworks

NumPy, Pandas, PyTorch, SciPy, TensorFlow, Torch7

Systems

Linux, OSX

Service

Reviewer

ICML 2018, NeurIPS 2018, ICLR 2019, NeurIPS Deep RL Workshop 2018

Admissions

CMU CSD MS 2014-2015

All Publications

Google Scholar

Preprints and Tech Reports

OpenFace: A general-purpose face recognition library with mobile applications
B. Amos, B. Ludwiczuk, and M. Satyanarayanan
CMU 2016
[P1] [abs] [pdf] [code]
Are Cloudlets Necessary?
Y. Gao, W. Hu, K. Ha, B. Amos, P. Pillai, and M. Satyanarayanan
CMU 2015
[P2] [abs] [pdf]
Adaptive VM handoff across cloudlets
K. Ha, Y. Abe, Z. Chen, W. Hu, B. Amos, P. Pillai, and M. Satyanarayanan
CMU 2015
[P3] [abs] [pdf]
QNSTOP-QuasiNewton Algorithm for Stochastic Optimization
B. Amos, D. Easterling, L. Watson, W. Thacker, B. Castle, and M. Trosset
VT 2014
[P4] [abs] [pdf]

Conference Proceedings

Differentiable MPC for End-to-end Planning and Control
B. Amos, I. Rodriguez, J. Sacks, B. Boots, and J. Kolter
NeurIPS 2018
[C1] [abs]
Depth-Limited Solving for Imperfect-Information Games
N. Brown, T. Sandholm, and B. Amos
NeurIPS 2018
[C2] [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
[C3] [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
[C4]
Task-based End-to-end Model Learning
P. Donti, B. Amos, and J. Kolter
NeurIPS 2017
[C5] [abs] [pdf] [code]
OptNet: Differentiable Optimization as a Layer in Neural Networks
B. Amos and J. Kolter
ICML 2017
[C6] [abs] [pdf] [code]
Input Convex Neural Networks
B. Amos, L. Xu, and J. Kolter
ICML 2017
[C7] [abs] [pdf] [code]
Collapsed Variational Inference for Sum-Product Networks
H. Zhao, T. Adel, G. Gordon, and B. Amos
ICML 2016
[C8] [abs] [pdf]
Applying machine learning classifiers to dynamic Android malware detection at scale
B. Amos, H. Turner, and J. White
IWCMC 2013
[C9] [abs] [pdf] [code]

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]

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]

Posters

Input-Convex Deep Networks
B. Amos and J. Kolter
ICLR Workshop 2016
[S1] [pdf]
Face Recognition for Context Sensitive IoT Systems
B. Amos and M. Satyanarayanan
HotMobile 2016
[S2] [pdf] [code]

Last updated on 2018-12-26