Brandon Amos
Research Scientist
Meta AI (FAIR)


I am a research scientist at Meta AI (FAIR) in NYC and study foundational topics in machine learning and optimization, recently involving reinforcement learning, control, optimal transport, and geometry. My research is on learning systems that understand and interact with our world and focuses on integrating structural information and domain knowledge into these systems to represent non-trivial reasoning operations. A key theme of my work in this space involves the use of optimization as a differentiable building block in larger architectures that are end-to-end learned. I believe that science should be open and reproducible and freely publish my research code to GitHub.


Ph.D. in Computer Science, Carnegie Mellon University (0.00/0.00)

Thesis: Differentiable Optimization-Based Modeling for Machine Learning
Advisor: J. Zico Kolter

2014 - 2019
B.S. in Computer Science, Virginia Tech (3.99/4.00)
2011 - 2014

Previous Positions

Research Assistant, Carnegie Mellon University (with J. Zico Kolter on ML and optimization)

2016 - 2019

Research Intern, Intel Labs, Santa Clara (with Vladlen Koltun on computer vision)


Research Intern, Google DeepMind, London (with Nando de Freitas and Misha Denil on RL)


Research Assistant, Carnegie Mellon University (with Mahadev Satyanarayanan on mobile systems)

2014 - 2016

Research Intern, Adobe Research, San Jose (with David Tompkins on distributed systems)


Research Assistant, Virginia Tech (with Layne Watson and David Easterling on optimization)

2013 - 2014

Research Assistant, Virginia Tech (with Jules White and Hamilton Turner on mobile systems)

2012 - 2014

Research Assistant, Virginia Tech (with Binoy Ravindran and Alastair Murray on compilers)

2012 - 2014

Software Intern, Snowplow (Scala development)

2013 - 2014

Software Intern, Qualcomm, San Diego (Python and C++ development)


Software Intern, Phoenix Integration, Virginia (C++, C#, and Java development)


Network Administrator Intern, Sunapsys, Virginia


Honors & Awards

ICLR Outstanding Reviewer
2016 - 2019
NSF Graduate Research Fellowship
2011 - 2014
Nine undergraduate scholarships

Roanoke County Public Schools Engineering, Salem-Roanoke County Chamber of Commerce, Papa John's, Scottish Rite of Freemasonry, VT Intelligence Community Conter for Academic Excellence, VT Pamplin Leader, VT Benjamin F. Bock, VT Gay B. Shober, VT I. Luck Gravett


Representative publications that I am a primary author on are highlighted.
[Google Scholar; 4853+ citations, h-index: 29+]


1. Tutorial on amortized optimization for learning to optimize over continuous domains [abs] [code]
Brandon Amos
arXiv 2022
2. Cross-Domain Imitation Learning via Optimal Transport [abs] [code]
Arnaud Fickinger, Samuel Cohen, Stuart Russell, and Brandon Amos
ICLR 2022
3. Semi-Discrete Normalizing Flows through Differentiable Tessellation [abs]
Ricky T. Q. Chen, Brandon Amos, and Maximilian Nickel
arXiv 2022
4. Meta Optimal Transport [abs] [code]
Brandon Amos, Samuel Cohen, Giulia Luise, and Ievgen Redko
arXiv 2022
5. Nocturne: a driving benchmark for multi-agent learning [abs] [code]
Eugene Vinitsky, Nathan Lichtlé, Xiaomeng Yang, Brandon Amos, and Jakob Foerster
arXiv 2022


6. On the model-based stochastic value gradient for continuous reinforcement learning [abs] [code] [slides]
Brandon Amos, Samuel Stanton, Denis Yarats, and Andrew Gordon Wilson
L4DC 2021 (Oral)
7. Riemannian Convex Potential Maps [abs] [code] [slides]
Samuel Cohen*, Brandon Amos*, and Yaron Lipman
ICML 2021
8. CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints [abs] [code]
Anselm Paulus, Michal Rolínek, Vít Musil, Brandon Amos, and Georg Martius
ICML 2021
9. Scalable Online Planning via Reinforcement Learning Fine-Tuning [abs]
Arnaud Fickinger, Hengyuan Hu, Brandon Amos, Stuart Russell, and Noam Brown
NeurIPS 2021
10. Aligning Time Series on Incomparable Spaces [abs] [code] [slides]
Samuel Cohen, Giulia Luise, Alexander Terenin, Brandon Amos, and Marc Peter Deisenroth
11. Learning Neural Event Functions for Ordinary Differential Equations [abs] [code]
Ricky T. Q. Chen, Brandon Amos, and Maximilian Nickel
ICLR 2021
12. Neural Spatio-Temporal Point Processes [abs] [code]
Ricky T. Q. Chen, Brandon Amos, and Maximilian Nickel
ICLR 2021
13. Improving Sample Efficiency in Model-Free Reinforcement Learning from Images [abs] [code]
Denis Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos, Joelle Pineau, and Rob Fergus
AAAI 2021
14. Neural Fixed-Point Acceleration for Convex Optimization [abs] [code]
Shobha Venkataraman* and Brandon Amos*
ICML AutoML Workshop 2021
15. Sliced Multi-Marginal Optimal Transport [abs]
Samuel Cohen, Alexander Terenin, Yannik Pitcan, Brandon Amos, Marc Peter Deisenroth, and K S Sesh Kumar
NeurIPS OTML Workshop 2021
16. Input Convex Gradient Networks [abs]
Jack Richter-Powell, Jonathan Lorraine, and Brandon Amos
NeurIPS OTML Workshop 2021
17. Imitation Learning from Pixel Observations for Continuous Control [abs]
Samuel Cohen, Brandon Amos, Marc Peter Deisenroth, Mikael Henaff, Eugene Vinitsky, and Denis Yarats
NeurIPS DeepRL Workshop 2021
18. MBRL-Lib: A Modular Library for Model-based Reinforcement Learning [abs] [code]
Luis Pineda, Brandon Amos, Amy Zhang, Nathan Lambert, and Roberto Calandra
arXiv 2021


19. The Differentiable Cross-Entropy Method [abs] [code] [slides]
Brandon Amos and Denis Yarats
ICML 2020
20. Objective Mismatch in Model-based Reinforcement Learning [abs]
Nathan Lambert, Brandon Amos, Omry Yadan, and Roberto Calandra
L4DC 2020
21. QNSTOP: Quasi-Newton Algorithm for Stochastic Optimization [abs] [code]
Brandon Amos, David Easterling, Layne T. Watson, William Thacker, Brent Castle, and Michael Trosset
22. Neural Potts Model [abs]
Tom Sercu, Robert Verkuil, Joshua Meier, Brandon Amos, Zeming Lin, Caroline Chen, Jason Liu, Yann LeCun, and Alexander Rives
MLCB 2020
23. Deep Riemannian Manifold Learning [abs]
Aaron Lou, Maximilian Nickel, and Brandon Amos
NeurIPS Geo4dl Workshop 2020


24. Differentiable Optimization-Based Modeling for Machine Learning [abs] [code]
Brandon Amos
Ph.D. Thesis 2019
25. Differentiable Convex Optimization Layers [abs] [code]
Akshay Agrawal*, Brandon Amos*, Shane Barratt*, Stephen Boyd*, Steven Diamond*, and J. Zico Kolter*
NeurIPS 2019
26. The Limited Multi-Label Projection Layer [abs] [code]
Brandon Amos, Vladlen Koltun, and J. Zico Kolter
arXiv 2019
27. Generalized Inner Loop Meta-Learning [abs] [code]
Edward Grefenstette, Brandon Amos, Denis Yarats, Phu Mon Htut, Artem Molchanov, Franziska Meier, Douwe Kiela, Kyunghyun Cho, and Soumith Chintala
arXiv 2019


28. Learning Awareness Models [abs]
Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, and Misha Denil
ICLR 2018
29. Differentiable MPC for End-to-end Planning and Control [abs] [code]
Brandon Amos, Ivan Dario Jimenez Rodriguez, Jacob Sacks, Byron Boots, and J. Zico Kolter
NeurIPS 2018
30. Depth-Limited Solving for Imperfect-Information Games [abs]
Noam Brown, Tuomas Sandholm, and Brandon Amos
NeurIPS 2018
31. Enabling Live Video Analytics with a Scalable and Privacy-Aware Framework [abs]
Junjue Wang, Brandon Amos, Anupam Das, Padmanabhan Pillai, Norman Sadeh, and Mahadev Satyanarayanan


32. OptNet: Differentiable Optimization as a Layer in Neural Networks [abs] [code] [slides]
Brandon Amos and J. Zico Kolter
ICML 2017
33. Input Convex Neural Networks [abs] [code] [slides]
Brandon Amos, Lei Xu, and J. Zico Kolter
ICML 2017
34. Task-based End-to-end Model Learning [abs] [code]
Priya L. Donti, Brandon Amos, and J. Zico Kolter
NeurIPS 2017
35. Quasi-Newton Stochastic Optimization Algorithm for Parameter Estimation of a Stochastic Model of the Budding Yeast Cell Cycle [abs]
Minghan Chen, Brandon Amos, Layne T. Watson, John Tyson, Yang Cao, Cliff Shaffer, Michael Trosset, Cihan Oguz, and Gisella Kakoti
36. You can teach elephants to dance: agile VM handoff for edge computing [abs]
Kiryong Ha, Yoshihisa Abe, Thomas Eiszler, Zhuo Chen, Wenlu Hu, Brandon Amos, Rohit Upadhyaya, Padmanabhan Pillai, and Mahadev Satyanarayanan
SEC 2017
37. An Empirical Study of Latency in an Emerging Class of Edge Computing Applications for Wearable Cognitive Assistance [abs]
Zhuo Chen, Wenlu Hu, Junjue Wang, Siyan Zhao, Brandon Amos, Guanhang Wu, Kiryong Ha, Khalid Elgazzar, Padmanabhan Pillai, Roberta Klatzky, Daniel Siewiorek, and Mahadev Satyanarayanan
SEC 2017
38. A Scalable and Privacy-Aware IoT Service for Live Video Analytics [abs] [code]
Junjue Wang, Brandon Amos, Anupam Das, Padmanabhan Pillai, Norman Sadeh, and Mahadev Satyanarayanan
ACM MMSys 2017 (Best Paper)


39. OpenFace: A general-purpose face recognition library with mobile applications [abs] [code]
Brandon Amos, Bartosz Ludwiczuk, and Mahadev Satyanarayanan
CMU 2016
40. Collapsed Variational Inference for Sum-Product Networks [abs]
Han Zhao, Tameem Adel, Geoff Gordon, and Brandon Amos
ICML 2016
41. Quantifying the impact of edge computing on mobile applications [abs]
Wenlu Hu, Ying Gao, Kiryong Ha, Junjue Wang, Brandon Amos, Zhuo Chen, Padmanabhan Pillai, and Mahadev Satyanarayanan
42. Privacy mediators: helping IoT cross the chasm [abs]
Nigel Davies, Nina Taft, Mahadev Satyanarayanan, Sarah Clinch, and Brandon Amos
HotMobile 2016

2015 and earlier

43. Edge Analytics in the Internet of Things [abs]
Mahadev Satyanarayanan, Pieter Simoens, Yu Xiao, Padmanabhan Pillai, Zhuo Chen, Kiryong Ha, Wenlu Hu, and Brandon Amos
IEEE Pervasive Computing 2015
44. Bad Parts: Are Our Manufacturing Systems at Risk of Silent Cyberattacks? [abs]
Hamilton Turner, Jules White, Jaime A. Camelio, Christopher Williams, Brandon Amos, and Robert Parker
IEEE Security & Privacy 2015
45. Early Implementation Experience with Wearable Cognitive Assistance Applications [abs]
Zhuo Chen, Lu Jiang, Wenlu Hu, Kiryong Ha, Brandon Amos, Padmanabhan Pillai, Alex Hauptmann, and Mahadev Satyanarayanan
WearSys 2015
46. The Case for Offload Shaping [abs]
Wenlu Hu, Brandon Amos, Zhuo Chen, Kiryong Ha, Wolfgang Richter, Padmanabhan Pillai, Benjamin Gilbert, Jan Harkes, and Mahadev Satyanarayanan
HotMobile 2015
47. Are Cloudlets Necessary? [abs]
Ying Gao, Wenlu Hu, Kiryong Ha, Brandon Amos, Padmanabhan Pillai, and Mahadev Satyanarayanan
CMU 2015
48. Adaptive VM handoff across cloudlets [abs]
Kiryong Ha, Yoshihisa Abe, Zhuo Chen, Wenlu Hu, Brandon Amos, Padmanabhan Pillai, and Mahadev Satyanarayanan
CMU 2015
49. Global Parameter Estimation for a Eukaryotic Cell Cycle Model in Systems Biology [abs]
Tricity Andrew, Brandon Amos, David Easterling, Cihan Oguz, William Baumann, John Tyson, and Layne T. Watson
SummerSim 2014
50. Applying machine learning classifiers to dynamic Android malware detection at scale [abs] [code]
Brandon Amos, Hamilton Turner, and Jules White
IWCMC 2013

Open Source Repositories

1. facebookresearch/amortized-optimization-tutorial | 119 | Tutorial on amortized optimization 2022
2. facebookresearch/theseus | 262 | Differentiable non-linear optimization library 2022
3. facebookresearch/meta-ot | 56 | Meta Optimal Transport 2022
4. facebookresearch/rcpm | 56 | Riemannian Convex Potential Maps 2021
5. facebookresearch/svg | 39 | Model-based stochastic value gradient 2021
6. facebookresearch/mbrl-lib | 635 | Model-based reinforcement learning library 2021
7. facebookresearch/dcem | 105 | The Differentiable Cross-Entropy Method 2020
8. facebookresearch/higher | 1.4k | PyTorch higher-order gradient and optimization library 2019
9. bamos/thesis | 271 | Ph.D. Thesis LaTeX source code 2019
10. cvxgrp/cvxpylayers | 1.3k | Differentiable Convex Optimization Layers 2019
11. locuslab/lml | 50 | The Limited Multi-Label Projection Layer 2019
12. locuslab/mpc.pytorch | 568 | Differentiable Model-Predictive Control 2018
13. locuslab/icnn | 238 | Input Convex Neural Networks 2017
14. locuslab/optnet | 390 | OptNet experiments 2017
15. locuslab/qpth | 528 | Differentiable PyTorch QP solver 2017
16. bamos/densenet.pytorch | 753 | PyTorch DenseNet implementation 2017
17. bamos/block | 268 | Intelligent block matrix constructions 2017
18. bamos/setGPU | 101 | Automatically use the least-loaded GPU 2017
19. bamos/dcgan-completion.tensorflow | 1.3k | Image completion with GANs 2016
20. cmusatyalab/openface | 14.4k | Face recognition with deep neural networks 2015
21. vtopt/qnstop | 10 | Fortran package for Quasi-newton stochastic optimization 2014
22. bamos/snowglobe | 27 | Haskell-driven, self-hosted web analytics with minimal configuration 2014
23. bamos/zsh-history-analysis | 184 | Analyze and plot your zsh history 2014
24. bamos/beamer-snippets | 106 | Beamer and TikZ snippets 2014
25. bamos/latex-templates | 356 | LaTeX templates 2013
26. cparse/cparse | 249 | C++ expression parser using Dijkstra's shunting-yard algorithm 2013
27. bamos/cv | 362 | Source for this CV: Creates LaTeX/Markdown from YAML/BibTeX 2013
28. bamos/python-scripts | 196 | Short and fun Python scripts 2013
29. bamos/reading-list | 185 | YAML reading list and notes system 2013
30. bamos/dotfiles | 239 | Linux, xmonad, emacs, vim, zsh, tmux 2012

Invited Talks

Slides for my major presentations are open-sourced at bamos/presentations.

1. End-to-end model learning for control, ICML Workshop on Decision Awareness in RL 2022
2. Differentiable optimization-based modeling for machine learning, CPAIOR Master Class 2022
3. Amortized optimization and learning to optimize, ICCOPT 2022
4. Modeling and learning paradigms for learning to optimize, SIAM MDS Minisymposium 2022
5. Learning for control with differentiable optimization and ODEs, Columbia University 2021
6. Differentiable optimization-based modeling for machine learning, IBM Research 2021
7. Differentiable optimization for control, Max Planck Institute (Tübingen) 2020
8. Differentiable optimization-based modeling for machine learning, Mila Seminar 2020
9. Deep Declarative Networks, ECCV Tutorial 2020
10. On differentiable optimization for control and vision, CVPR Deep Declarative Networks Workshop 2020
11. Differentiable optimization-based modeling for machine learning, Caltech CS 159 (Guest Lecture) 2020
12. Unrolled optimization for learning deep energy models, SIAM MDS Minisymposium 2020
13. Differentiable optimization-based modeling for machine learning, NYU CILVR Seminar 2019
14. Differentiable optimization-based modeling for machine learning, INFORMS 2019
15. Differentiable optimization-based modeling for machine learning, Facebook AI Research 2019
16. Differentiable optimization-based modeling for machine learning, ISMP 2018
17. Differentiable optimization-based modeling for machine learning, Google Brain 2018
18. Differentiable optimization-based modeling for machine learning, Bosch Center for AI 2018
19. Differentiable optimization-based modeling for machine learning, Waymo Research 2018
20. Differentiable optimization-based modeling for machine learning, Tesla AI 2018
21. Differentiable optimization-based modeling for machine learning, NVIDIA Robotics 2018
22. Differentiable optimization-based modeling for machine learning, Salesforce Research 2018
23. Differentiable optimization-based modeling for machine learning, OpenAI 2018
24. Differentiable optimization-based modeling for machine learning, NNAISENSE 2018
25. Differentiable optimization and control, UC Berkeley 2018

Interns and Students

Aaron Lou (visiting FAIR from Cornell and Stanford) 2020 - 2022
Eugene Vinitsky (visiting FAIR from Berkeley) 2021 - 2022
Arnaud Fickinger (visiting FAIR from Berkeley) 2021 - 2022
Samuel Cohen (visiting FAIR from UCL) 2021 - 2022
Ricky Chen (visiting FAIR from Toronto, now: scientist at FAIR) 2020
Paul Liang (visiting FAIR from CMU) 2020
Phillip Wang (at CMU, now: CEO at Gather) 2018

Professional Activities

NeurIPS Learning Meets Combinatorial Optimization Workshop Organizer 2020
CVPR Deep Declarative Networks Workshop Organizer 2020
ECCV Deep Declarative Networks Tutorial Organizer 2020
CMU CSD MS Admissions 2014 - 2015


Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE International Conference on Computer Vision (ICCV)
IEEE International Conference on Robotics and Automation (ICRA)
AAAI Conference on Artificial Intelligence
Optimization Letters


Graduate AI (CMU 15-780), TA S2017
Distributed Systems (CMU 15-440/640), TA S2016
Software Design and Data Structures (VT CS2114), TA S2013


Programming C, C++, Fortran, Haskell, Java, Lua, Make, Mathematica, Python, R, Scala
Frameworks JAX, NumPy, Pandas, PyTorch, SciPy, TensorFlow, Torch7
Toolbox Linux, emacs, vim, evil, org, mu4e, xmonad, git, tmux, zsh

Last updated on 2022-06-23