I'm a Member of Technical Staff at Merge Labs, where I work on machine learning problems at the intersection of signal processing and inference. Before that, I was a Senior Machine Learning Engineer on Tesla's Supply Chain team, where I built distributed reinforcement learning systems (GRPO, PPO, DQN) for 3D bin-packing and warehouse automation, alongside mixed-integer programming for constrained routing and Bayesian deep learning for forecasting.
My academic background is in the intersection of harmonic analysis and matrix analysis, and their uses in applied problems such as quantum tomography, speech recognition, radar reconstruction, and machine learning. My research centered on frame theory and Lipschitz analysis à la Kirszbraun, drawing on differential geometry and the theory of analytic varieties (Whitney stratifications) to understand the phase retrieval problem in the case of impure states. I remain interested in using Lipschitz analysis and differential geometry to understand and improve generative models, as well as in higher order Fourier analysis and its applications to signal processing.
cbartondock@gmail.com
Member of Technical Staff at Merge Labs
Employment History
Member of Technical Staff, Merge Labs
Senior Machine Learning Engineer, Tesla, Supply Chain Org.
Reinforcement learning (distributed implementations of GRPO, PPO, DQN) for 3D bin-packing, warehouse slotting and picking automation; mixed integer programming for constrained routing; Bayesian deep learning for hierarchical/multivariate forecasting. Owned the infrastructure for Supply Chain's Digital Twin and distributed RL framework. 3D bin-packing algorithm is under IP review for a potential patent.
Norbert Wiener Assistant Professor, Tufts University, Dept. of Mathematics.
Research on signal processing, uncertainty principles in frame theory, inverse problems arising from quantum computing, and the differential geometry of generative machine learning.
Ph.D. Student and Teaching Assistant, University of Maryland, Dept. of Mathematics.
Taught undergraduate mathematics and performed research on harmonic analysis, frame theory, and machine learning.
Education
Thesis: U(r) Phase Retrieval, Local Normalizing Flows, and Higher Order Fourier Transforms
Graduated with honors. Undergraduate thesis: Long Range Dispersal Kernels; Theory and Applications
Publications
Ph.D. Thesis- C. B. Dock, “U(r) Phase Retrieval, Local Normalizing Flows, and Higher Order Fourier Transforms,” Ph.D. dissertation, University of Maryland, College Park, 2022.
- Lipschitz Analysis of Generalized Phase Retrievable Matrix Frames Chris B. Dock, Radu Balan. Published in SIAM Journal on Matrix Analysis and Applications, vol. 43, no. 3, pp. 1518–1571, 2022.
- Measuring Quasiperiodicity Suddhasattwa Das, Chris B. Dock, Yoshitaka Saiki, Martin Salgado-Flores, Evelyn Sander, Jin Wu, James A. Yorke. Published in Europhysics Letters, vol. 114, no. 4, p. 40005, 2016.
- Lipschitz Embeddings and Riemannian Properties of Spaces of Low-Rank Symmetric Matrices. Chris B. Dock, Radu Balan. In The 8th International Conference on Computational Harmonic Analysis, University of Vienna, 2022.
- VQ-Flows: Vector Quantized Local Normalizing Flows Sahil Sidheekh, Chris B. Dock, Tushar Jain, Radu Balan, Maneesh K. Singh. Published as a conference paper in Uncertainty in Artificial Intelligence, PMLR, 2022, pp. 1835–1845.
Other Work
Talks- Lipschitz Analysis of Generalized Phase Retrievable Frames at AMS Fall Western Sectional Meeting, Special Session on Harmonic Analysis: Geometry, Frames, and Sampling, University of New Mexico (2021)
- Lipschitz Analysis of Noisy Quantum Inference as Phase Retrieval at Approximation Theory 16, Vanderbilt University (2019)
- Towards an affine invariant generative model
- Gabor Frames, the Zak Transform and Balian-Low
- Fast iterative methods for reconstruction from non-uniform samples
- Wavelet packets and Walsh functions
- Tufts University — Math 123 Mathematical Machine Learning, Math 165 Probability Theory (Fall 2024); Math 133 Complex Analysis (Spring 2024); Math 135 Real Analysis I, Math 123 Mathematical Machine Learning (Fall 2023); Math 126 Numerical Linear Algebra (Spring 2023); Mathematical Machine Learning, Ordinary Differential Equations (Fall 2022)
- ENES 106: Single Variable Calculus, University of Maryland (Summer 2022)
- University of Maryland (sole contact classes) — Math 246 Differential Equations (Summer 2021); Math 107 Modeling and Probability (Summer/Spring 2020); Math 212 Teaching Numbers and Operations (Fall 2019); Math 113 College Algebra & Trigonometry (Fall 2018)
Awards
“In recognition of your contribution, impact and effort to foster a culture of innovation, drive, collaboration and trust.”
Awarded annually to the author of an outstanding Ph.D. thesis in computational mathematics.
Awarded by the Physics Department for high quality undergraduate research. Received twice.
Skills
ML Frameworks — PyTorch, TensorFlow, Gymnasium, MuJoCo
Web — HTML/CSS/JavaScript/TypeScript, React/React Native, Django, SQL, GraphQL
Mathematics — signal processing, multilinear algebra, differential geometry, probability theory, stochastic processes, integer/linear/quadratic programming, Lagrangian/Hamiltonian dynamics, dynamical systems
Machine Learning — reinforcement learning, normalizing flows, Bayesian optimization, policy gradient methods, Wasserstein metrics, functional iteration
Languages — fluent in English and French