Bio
I am a quantitative researcher at Citadel Securities in Chicago. I received a PhD from the Department of Statistics at the University of Washington where I was advised by Emily B. Fox. Prior to my PhD at the University of Washington, I received a BS and MS degree from the Department of Applied Mathematics at the University of Colorado where I was advised by Aaron Clauset.
Research
My research interests are in scalable approximate inference methods for machine learning, specifically using deterministic Bayesian approximations (e.g. Expectation Propagation and Variational Inference) and stochastic gradient MCMC methods (e.g. SGLD). My research projects include:
- Stochastic Gradient Methods for Time Series
- Adaptive Truncation of Backpropagation in Recurrent Neural Networks
- Community Detection in Weighted Network Data using Variational Inference
- Time Series Clustering using Expectation Propagation
Experience
- Quantitative Researcher, Citadel Securites (03/20-Current)
- Applying statistical/ML techinques and engineering skills to model markets, test hypotheses and develop proprietary algorithms.
- Research Intern, Microsoft AI and Research (06/17-09/17)
- Worked with Consumer Data & Analytics team on short-form text clustering.
- Developed an online feature extractor using RNNs and non-parametric clustering.
- Research Scientist Intern, Amazon (06/16-09/16)
- Worked with the Kindle devices demand planning team on forecasting sales.
- Developed a custom R package for prototyping new models.
- Tested and integrated quantile random forests to improve short-term forecasting
- Machine Learning Intern, Dato (now Turi/Apple) (06/15-09/15)
- Researched, developed, and shipped a new itemset mining toolkit as part of GraphLab Create's machine learning applications library.
Publications
- Aicher, C. (2020). Scalable Learning in Latent State Sequence Models [PhD thesis]. University of Washington.
[PDF]
BibTex
@phdthesis{aicher2020scalable, title = {Scalable Learning in Latent State Sequence Models}, author = {Aicher, Christopher}, school = {University of Washington}, year = {2020}, link = {https://digital.lib.washington.edu/researchworks/handle/1773/45550} }
- Aicher, C., Foti, N. J., & Fox, E. B. (2019). Adaptively Truncating Backpropagation Through Time to Control Gradient Bias. Uncertainty in Artificial Intelligence.
[PDF]
[Code]
 
BibTex
@article{aicher2019tbptt, title = {Adaptively Truncating Backpropagation Through Time to Control Gradient Bias}, author = {Aicher, Christopher and Foti, Nicholas J. and Fox, Emily B.}, journal = {Uncertainty in Artificial Intelligence}, year = {2019}, month = may, link = {https://arxiv.org/abs/1905.07473}, code = {https://github.com/aicherc/adaptive_tbptt} }
- Aicher, C., Putcha, S., Nemeth, C., Fearnhead, P., & Fox, E. B. (2019). Stochastic Gradient MCMC for Nonlinear State Space Models. ArXiv Preprint ArXiv:1901.10568.
[PDF]
[Code]
 
BibTex
@article{aicher2019nonlinear, title = {Stochastic Gradient MCMC for Nonlinear State Space Models}, author = {Aicher, Christopher and Putcha, Srshti and Nemeth, Christopher and Fearnhead, Paul and Fox, Emily B.}, journal = {arXiv preprint arXiv:1901.10568}, year = {2019}, month = jan, link = {https://arxiv.org/abs/1901.10568}, code = {https://github.com/aicherc/sgmcmc_ssm_code} }
- Aicher, C., Ma, Y.-A., Foti, N. J., & Fox, E. B. (2019). Stochastic Gradient MCMC for State Space Models. SIAM Journal on Mathematics of Data Science, 1(3), 555–587.
[PDF]
[Code]
 
BibTex
@article{aicher2019stochastic, title = {Stochastic Gradient MCMC for State Space Models}, author = {Aicher, Christopher and Ma, Yi-An and Foti, Nicholas J and Fox, Emily B}, journal = {SIAM Journal on Mathematics of Data Science}, volume = {1}, number = {3}, pages = {555--587}, year = {2019}, publisher = {SIAM}, link = {https://arxiv.org/abs/1810.09098}, code = {https://github.com/aicherc/sgmcmc_ssm_code} }
- Aicher, C., & Fox, E. B. (2018). Approximate Collapsed Gibbs Clustering with Expectation Propagation. ArXiv Preprint ArXiv:1807.07621.
[PDF]
[Code]
 
BibTex
@article{aicher2018approximate, title = {Approximate Collapsed Gibbs Clustering with Expectation Propagation}, author = {Aicher, Christopher and Fox, Emily B.}, journal = {arXiv preprint arXiv:1807.07621}, year = {2018}, month = jul, link = {https://arxiv.org/abs/1807.07621}, code = {https://github.com/aicherc/EP_Collapsed_Gibbs} }
- Simonen, K., Huang, M., Aicher, C., & Morris, P. (2018). Embodied Carbon as a Proxy for the Environmental Impact of Earthquake Damage Repair. Energy and Buildings.
[PDF]
BibTex
@article{simonen2018embodied, title = {Embodied Carbon as a Proxy for the Environmental Impact of Earthquake Damage Repair}, author = {Simonen, K and Huang, M and Aicher, C and Morris, P}, journal = {Energy and Buildings}, year = {2018}, month = jan, link = {https://www.sciencedirect.com/science/article/pii/S0378778817319710} }
- Aicher, C., & Fox, E. B. (2016). Scalable Clustering of Correlated Time Series Using Expectation Propagation. SIGKDD Workshop on MiLeTS.
[PDF]
[Code]
 
BibTex
@article{aicherc2016scalable, title = {Scalable Clustering of Correlated Time Series Using Expectation Propagation}, author = {Aicher, Christopher and Fox, Emily B.}, journal = {SIGKDD Workshop on MiLeTS}, year = {2016}, code = {https://github.com/aicherc/EP_Collapsed_Gibbs} }
- Aicher, C., Jacobs, A. Z., & Clauset, A. (2015). Learning Latent Block Structure in Weighted Networks. Journal of Complex Networks, 3(2), 221–248.
[PDF]
[Code]
 
BibTex
@article{aicher2015learning, title = {Learning Latent Block Structure in Weighted Networks}, author = {Aicher, Christopher and Jacobs, Abigail Z and Clauset, Aaron}, journal = {Journal of Complex Networks}, volume = {3}, number = {2}, pages = {221--248}, year = {2015}, publisher = {Oxford University Press}, link = {http://arxiv.org/abs/1404.0431}, code = {http://tuvalu.santafe.edu/%7Eaaronc/wsbm/} }
- Aicher, C., Jacobs, A. Z., & Clauset, A. (2013). Adapting the Stochastic Block Model to Edge-Weighted Networks. ICML Workshop on Structured Learning.
[PDF]
[Code]
 
BibTex
@article{aicher2013adapting, title = {Adapting the Stochastic Block Model to Edge-Weighted Networks}, author = {Aicher, Christopher and Jacobs, Abigail Z and Clauset, Aaron}, journal = {ICML Workshop on Structured Learning}, year = {2013}, link = {http://arxiv.org/abs/1305.5782}, code = {http://tuvalu.santafe.edu/%7Eaaronc/wsbm/} }
Teaching
- Teaching Assistant (University of Washington)
- Statistical Methods in Engineering and Science (STAT 390)
- Learning Assistant (University of Colorado)
- Applied Probability (APPM 3570)
- Mathematical Statistics (APPM 4570)
- Matrix Methods and Applications (APPM 3310)
- Calculus 2 (APPM 1360)