Daniel Lundén

I am a PhD student at the School of Electrical Engineering and Computer Science, Division of Software and Computer Systems, KTH Royal Institute of Technology.

I do research in probabilistic programming, an interdisciplinary field with influences from computer science, probability theory, statistics, machine learning, and artificial intelligence. In my research, I focus on developing mathematical foundations and efficient compilers for probabilistic programming languages. I am particularly interested in programming language theory, compilers, and static program analysis.

My principal supervisor is David Broman (KTH), and my assistant supervisors are Lawrence Murray (Uber AI) and Joakim Jaldén (KTH).

Awards

Distinguished Artifact Award at the European Symposium on Programming, 2022.

Commissions of Trust

Doctoral student representative in the ICT doctoral program council, 2018 – .

Program Committees and Reviewing Assignments

• PROBPROG program committee member, 2021.
• NeurIPS reviewer, 2021.

Teaching

• Teacher in IS1200 Computer Hardware Engineering, August 2017 – .
• Teacher in IS1500 Computer Organization and Components, August 2017 – .

Conference and Journal Articles

• Daniel Lundén, Gizem Çaylak, Fredrik Ronquist, David Broman. Automatic Alignment in Higher-Order Probabilistic Programming Languages. To appear at ESOP 2023. [ ESOP ]
• Daniel Lundén, Joey Öhman, Jan Kudlicka, Viktor Senderov, Fredrik Ronquist, David Broman. Compiling Universal Probabilistic Programming Languages with Efficient Parallel Sequential Monte Carlo Inference. ESOP 2022. [ SpringerLink | DiVA | PDF | arXiv (extended) | PDF (extended) ]
• Daniel Lundén, Johannes Borgström, and David Broman. Correctness of Sequential Monte Carlo Inference for Probabilistic Programming Languages. ESOP 2021. [ SpringerLink | DiVA | PDF | arXiv (extended) | PDF (extended) ]
• Fredrik Ronquist, Jan Kudlicka, Viktor Senderov, Johannes Borgström, Nicolas Lartillot, Daniel Lundén, Lawrence Murray, Thomas B. Schön, and David Broman. Universal probabilistic programming offers a powerful approach to statistical phylogenetics. In Communications Biology 4. 2021. [ Nature | bioRxiv | PDF ]
• Lawrence M. Murray, Daniel Lundén, Jan Kudlicka, David Broman, and Thomas Schön. Delayed Sampling and Automatic Rao-Blackwellization of Probabilistic Programs. In Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. AISTATS 2018. [ AISTATS | PDF ]

Preprints

• Daniel Lundén, Lars Hummelgren, Jan Kudlicka, Oscar Eriksson, and David Broman. Suspension Analysis and Selective Continuation-Passing Style for Higher-Order Probabilistic Programming Languages. 2023. [ DiVA | PDF | arXiv ]

Workshop Extended Abstracts

• Daniel Lundén, Joey Öhman, David Broman. Compilation of Universal Probabilistic Programs to GPGPUs. PROBPROG 2020. [ PROBPROG | PDF | Poster ]
• Daniel Lundén, David Broman, Fredrik Ronquist, and Lawrence M. Murray. Automatic Discovery of Static Structures in Probabilistic Programs. PROBPROG 2018. [ PROBPROG | PDF | Poster ]
• Daniel Lundén, David Broman, and Lawrence M. Murray. Combining Static and Dynamic Optimizations Using Closed-Form Solutions. PPS 2018. [ PPS |  |  ]

Theses

• Daniel Lundén. Correct and Efficient Monte Carlo Inference for Universal Probabilistic Programming Languages. Doctoral thesis, KTH Royal Institute of Technology. 2023. [ DiVA | PDF ]
• Daniel Lundén. Delayed sampling in the probabilistic programming language Anglican. Master's thesis, KTH Royal Institute of Technology. 2017. [ DiVA | PDF ]
• Erik Forsblom, Daniel Lundén. Factoring integers with parallel SAT solvers. Bachelor’s thesis, KTH Royal Institute of Technology. 2015. [ DiVA | PDF ]