Carson Eisenach

Carson Eisenach

Senior Applied Scientist, Amazon

Biography

Carson is a Senior Machine Learning Scientist at Amazon where his research focuses on applying reinforcement learning to supply chain optimization. Other projects he currently works on include developing deep learning models for probabilistic time-series forecasting.

Before joining Amazon, Carson received his PhD in June 2019 from the ORFE department at Princeton University. While at Princeton, he was advised by Han Liu and his research focused on optimization, as applied to high-dimensional inference problems and stochastic decision-making. From September 2017 until August 2018, Carson interned at the Tencent AI Lab in Bellevue, Washington.

Interests
  • Reinforcement Learning
  • Artificial Intelligence
  • Statistical Learning
Education

  • PhD in Operations Research and Financial Engineering, 2019

    Princeton University

  • M.A. in Operations Research and Financial Engineering, 2016

    Princeton University

  • B.A. in Mathematics and Computer Science, 2014

    Williams College

Featured Publications

Learning an Inventory Control Policy with General Inventory Arrival Dynamics
In this paper we address the problem of learning and backtesting inventory control policies in the presence of general arrival dynamics …
Preprint
Learning an Inventory Control Policy with General Inventory Arrival Dynamics
Deep Inventory Management
This work provides a Deep Reinforcement Learning approach to solving a periodic review inventory control system with stochastic vendor …
Preprint
Deep Inventory Management
High Dimensional Inference for Cluster-Based Graphical Models
Motivated by modern applications in which one constructs graphical models based on a very large number of features, this paper …
Preprint PDF Project
High Dimensional Inference for Cluster-Based Graphical Models
Efficient, Certifiably Optimal Clustering with Applications to Latent Variable Graphical Models
We consider SDP relaxation methods for data and variable clustering problems, which have been shown in the literature to have good …
Preprint PDF Project Project
Efficient, Certifiably Optimal Clustering with Applications to Latent Variable Graphical Models
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
Many complex domains, such as robotics control and real-time strategy (RTS) games, require an agent to learn a continuous control. In …
Preprint Code Project
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications

Recent Publications

Sohrab Andaz, Carson Eisenach, Dhruv Madeka, Kari Torkkola, Randy Jia, Dean Foster, Sham Kakade (2023). Learning an Inventory Control Policy with General Inventory Arrival Dynamics.

Preprint

Dhruv Madeka, Kari Torkkola, Carson Eisenach, Anna Luo, Dean Foster, Sham Kakade (2022). Deep Inventory Management.

Preprint

Sitan Yang, Carson Eisenach, Dhruv Madeka (2022). MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation. KDD MILETS 2022.

Preprint PDF

Carson Eisenach, Yagna Patel, Dhruv Madeka (2020). MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention.

Preprint

Carson Eisenach, Florentina Bunea, Yang Ning, Claudiu Dinicu (2020). High Dimensional Inference for Cluster-Based Graphical Models. JMLR.

Preprint PDF Project

Carson Eisenach, Han Liu (2019). Efficient, Certifiably Optimal Clustering with Applications to Latent Variable Graphical Models. Mathematical Programming Series B.

Preprint PDF Project Project

Carson Eisenach, Haichuan Yang, Ji Liu, Han Liu (2019). Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications. ICLR'19.

Preprint Code Project

Carson Eisenach, Zhuoran Yang (2018). Natural Policy Gradient for Exponential Families. Technical Report.

PDF Code Project

Carson Eisenach, Zhaoran Wang, Han Liu (2016). Nonparametrically Learning Activation Functions in Deep Neural Nets. Technical Report.

PDF Project

Recent & Upcoming Talks

High Dimensional Inference for G-Block Latent Variable Graphical Models
Sep 1, 2016 1:00 PM — 3:00 PM Ithaca, NY
Is it possible to square the circle?
Apr 1, 2013 1:00 PM — 3:00 PM Williamstown, MA
Marginal Policy Gradients for Complex Control
Jun 17, 2018 1:00 PM — 3:00 PM New Brunswick, NJ
Topics in Multi-agent Reinforcement Learning
Nov 7, 2018 1:00 PM — 3:00 PM Bethlehem, PA

Recent Posts

Torchkit: A toolkit for RL research built using PyTorch
Torchkit v0 now available on Github.
Feb 17, 2019 1 min read
Project
Torchkit: A toolkit for RL research built using PyTorch
GFORCE
GFORCE released on CRAN.
Jun 15, 2018 1 min read
Project Project
GFORCE

Teaching

I have served as a teaching assistant for the following courses at Princeton University:

  • ORF245: Fundamentals of Statistics (Fall 2015, Fall 2016, Spring 2019)
  • ORF307: Optimization (Spring 2016, Spring 2017)
  • ORF405: Regression and Time Series (Fall 2018)

Contact