MENU

Daniel Kuhn

Daniel Kuhn
Prof. Dr.
Daniel Kuhn
PI
EPF Lausanne
daniel.kuhn@epfl.ch
Curriculum Vitae
Aiming to optimize engineered systems affected by uncertainty, the NCCR Automation is right at the heart of my long-standing research interests.

Daniel Kuhn is Professor of Operations Research at the College of Management of Technology at EPFL, where he holds the Chair of Risk Analytics and Optimization. Before joining EPFL, he was a faculty member at Imperial College London (2007–2013) and a postdoctoral researcher at Stanford University (2005–2006). He received a Ph.D. in Economics from the University of St. Gallen in 2004 and an M.Sc. in Theoretical Physics from ETH Zürich in 1999. His research interests revolve around stochastic programming and robust optimization.

Scientific Publications

Published
Discrete Optimal Transport with Independent Marginals is #P-Hard
SIAM Journal on Optimization
Vol 33 No 2 Pages 589-614
Bahar Taskesen, Soroosh Shafiezadeh Abadeh, Daniel Kuhn, Karthik Natarajan
Doi.org
Published
PIQP: A Proximal Interior-Point Quadratic Programming Solver
62nd IEEE Conference on Decision and Control
Roland Schwan, Yuning Jiang, Daniel Kuhn, Colin Jones
Collection
Published
Stability Verification of Neural Network Controllers using Mixed-Integer Programming
IEEE Transactions on Automatic Control
Roland Schwan, Colin Jones, Daniel Kuhn
Doi.org Collection Arxiv.org
Published
Robust Generalization despite Distribution Shift via Minimum Discriminating Information
Conference on Neural Information Processing Systems (NeurIPS 2021)
Vol 34 Pages 29754-29767
Tobias Sutter, Andreas Krause, Daniel Kuhn
Doi.org Collection
Published
Efficient Learning of a Linear Dynamical System with Stability Guarantees
IEEE Transactions on Automatic Control
Vol 68 No 5 Pages 2790-2804
Wouter Jongeneel, Tobias Sutter, Daniel Kuhn
Doi.org Collection
Distributionally Robust Optimization with Markovian Data
38th International Conference on Machine Learning (ICML 2021)
Mengmeng Li, Tobias Sutter, Daniel Kuhn
Collection
Published
Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution
Mathematical Programming
Vol 199 Pages 1033-1106
Bahar Taskesen, Soroosh Shafiezadeh Abadeh, Daniel Kuhn
Collection

Research projects

Title
Principal Investigators

Dynamic distributionally robust optimization and control

Daniel Kuhn

Summary

In this project we aim to transfer the powerful modern methods of distributionally robust optimization to dynamic decision problems and optimal control problems. Important tasks to be addressed include the derivation of tractable convex reformulations or approximations for the original distributionally robust optimization problems, the design of customized first-order methods for their efficient solution, the derivation of out-of-sample performance and asymptotic consistency guarantees, and the study of the time consistency properties of the new control models.

People involved

Daniel Kuhn
Wouter Jongeneel
Daniel Kuhn, Wouter Jongeneel
Dynamic distributionally robust optimization and control
Daniel Kuhn

In this project we aim to transfer the powerful modern methods of distributionally robust optimization to dynamic decision problems and optimal control problems. Important tasks to be addressed include the derivation of tractable convex reformulations or approximations for the original distributionally robust optimization problems, the design of customized first-order methods for their efficient solution, the derivation of out-of-sample performance and asymptotic consistency guarantees, and the study of the time consistency properties of the new control models.

Daniel Kuhn
Wouter Jongeneel
Daniel Kuhn, Wouter Jongeneel
145
e4519ae2-415b-45fa-b38e-d38520ca7a34

Scalable market mechanisms for deploying massive amounts of distributed energy resources

Daniel Kuhn, Gabriela Hug

Summary

We study how flexible devices, consumers and producers can participate in an automated fashion in an energy market that yields efficient market outcomes. As the availability of distributed resources in terms of production and flexibility is uncertain, probabilistic approaches for the automated bidding but also for the determination of the required reserves are necessary. Given that distributions of the willingness of the participants to accept prices are unknown, we intend to formulate and explore distributionally robust optimization models.

People involved

Daniel Kuhn
Daniel Kuhn, Gabriela Hug
Scalable market mechanisms for deploying massive amounts of distributed energy resources
Daniel Kuhn, Gabriela Hug

We study how flexible devices, consumers and producers can participate in an automated fashion in an energy market that yields efficient market outcomes. As the availability of distributed resources in terms of production and flexibility is uncertain, probabilistic approaches for the automated bidding but also for the determination of the required reserves are necessary. Given that distributions of the willingness of the participants to accept prices are unknown, we intend to formulate and explore distributionally robust optimization models.

Daniel Kuhn
Daniel Kuhn, Gabriela Hug
130
c3a694bf-c218-4f8d-815d-02b060f2519d

Learning Fast Convex Optimizers

Colin Jones, Daniel Kuhn, Silvia Mastellone

Summary

This project will study formal methods for reduced complexity design and verification of embedded optimization techniques for the control of high-speed nonlinear constrained systems. We will focus on machine learning techniques for differentiable parametric optimization and their application to the control of fast, nonlinear dynamic systems with a power conversion system taken as an important exemplar case study.

People involved

Colin Jones
Daniel Kuhn
Silvia Mastellone
Roland Schwan
Colin Jones, Daniel Kuhn, Silvia Mastellone, Roland Schwan
Learning Fast Convex Optimizers
Colin Jones, Daniel Kuhn, Silvia Mastellone

This project will study formal methods for reduced complexity design and verification of embedded optimization techniques for the control of high-speed nonlinear constrained systems. We will focus on machine learning techniques for differentiable parametric optimization and their application to the control of fast, nonlinear dynamic systems with a power conversion system taken as an important exemplar case study.

Colin Jones
Daniel Kuhn
Silvia Mastellone
Roland Schwan
Colin Jones, Daniel Kuhn, Silvia Mastellone, Roland Schwan
114
8a64bfd0-5a4a-4ae8-951a-bad586329d22

Distributionally robust reinforcement learning

Daniel Kuhn, Andreas Krause

Summary

This project uses ideas from mathematical optimization and learning theory to derive statistical guarantees for reinforcement learning (RL). While there has recently been significant progress in the understanding of finite-sample guarantees for the linear quadratic regulator (LQR) problem, it remains unclear how to generalize these results beyond the LQR setting. We plan to establish a principled approach to RL based on distributionally robust optimization with the goal to derive statistical guarantees for RL problems beyond the LQR setup. We also aim to develop efficient computational algorithms.

People involved

Daniel Kuhn
Andreas Krause
Tobias Sutter
Daniel Kuhn, Andreas Krause, Tobias Sutter
Distributionally robust reinforcement learning
Daniel Kuhn, Andreas Krause

This project uses ideas from mathematical optimization and learning theory to derive statistical guarantees for reinforcement learning (RL). While there has recently been significant progress in the understanding of finite-sample guarantees for the linear quadratic regulator (LQR) problem, it remains unclear how to generalize these results beyond the LQR setting. We plan to establish a principled approach to RL based on distributionally robust optimization with the goal to derive statistical guarantees for RL problems beyond the LQR setup. We also aim to develop efficient computational algorithms.

Daniel Kuhn
Andreas Krause
Tobias Sutter
Daniel Kuhn, Andreas Krause, Tobias Sutter
106
7e6307b6-fce1-4184-b451-bb44a15e437a

Online distributionally robust optimization with streaming data

Florian Dörfler, John Lygeros, Daniel Kuhn

Summary

Recent years have seen a surge of academic and industrial interest in distributionally robust optimization, where the probability distribution of the uncertain problem parameters is itself uncertain and one seeks decisions that are optimal in view of the most adverse distribution within a given ambiguity set. In this project we will study online distributionally robust optimization with streaming data. The key motivation is that dynamic stochastic processes (as encountered in control, estimating, and filtering problems) demand recursive and online solutions with real-time computational constraints. We plan to implement our approaches on various energy system platforms.

People involved

Florian Dörfler
Daniel Kuhn
Soroosh Shafiezadeh Abadeh
Florian Dörfler, John Lygeros, Daniel Kuhn, Soroosh Shafiezadeh Abadeh
Online distributionally robust optimization with streaming data
Florian Dörfler, John Lygeros, Daniel Kuhn

Recent years have seen a surge of academic and industrial interest in distributionally robust optimization, where the probability distribution of the uncertain problem parameters is itself uncertain and one seeks decisions that are optimal in view of the most adverse distribution within a given ambiguity set. In this project we will study online distributionally robust optimization with streaming data. The key motivation is that dynamic stochastic processes (as encountered in control, estimating, and filtering problems) demand recursive and online solutions with real-time computational constraints. We plan to implement our approaches on various energy system platforms.

Florian Dörfler
Daniel Kuhn
Soroosh Shafiezadeh Abadeh
Florian Dörfler, John Lygeros, Daniel Kuhn, Soroosh Shafiezadeh Abadeh
103
eba884a0-fcfd-4541-970c-a9265f02a32d