Christian A. Naesseth

Christian A. Naesseth is an Assistant Professor of Machine Learning at the University of Amsterdam, where he is a member of the Amsterdam Machine Learning Lab and serves as lab manager of the UvA-Bosch Delta Lab 2. He is also an ELLIS member, actively contributing to the European AI research community. His work bridges theoretical machine learning with practical applications across scientific domains.

• University of Amsterdam - Faculty of Science
• Amsterdam Machine Learning Lab (AMLab)
• UvA-Bosch Delta Lab 2 (Lab Manager)
• ELLIS Institute member

Naesseth's research focuses on generative modeling, uncertainty quantification, and probabilistic machine learning. His work spans diffusion models, flow matching techniques, stochastic differential equations, and their applications in scientific domains. He has made significant contributions to simulation-free training frameworks like SDE Matching, which eliminates the need for discretization and simulation when fitting latent SDE models to data. His research also addresses critical challenges in uncertainty quantification, including conformal prediction, risk monitoring in test-time adaptation, and multiple hypothesis testing.

His recent publications demonstrate a consistent focus on improving efficiency and reliability in generative modeling while maintaining theoretical rigor. The work on SDE Matching represents a major advancement in training efficiency for latent stochastic differential equations, achieving speed improvements of several orders of magnitude. His research on risk monitoring and conformal prediction addresses practical deployment challenges for AI systems operating under distribution shift.

• Best Workshop Paper Award at AABI 2025 for SDE Matching
• 100% acceptance rate across major ML conferences in the 2024-2025 cycle (5/5 NeurIPS, 2/2 AISTATS, 2/2 ICML, 1/1 UAI)

Naesseth actively mentors PhD students and postdocs, including Grigory Bartosh, Hany Abdulsamad, and several visiting researchers from institutions worldwide. He serves as program chair for AABI 2024 and has been involved in organizing multiple workshops at major conferences including ICML and NeurIPS. His lab has secured funding through collaborations with Bosch and likely other industry partners, supporting postdoctoral researchers and PhD students working at the intersection of theory and applications.

He leads the UvA-Bosch Delta Lab 2, which focuses on advancing the theoretical foundations of machine learning while developing practical applications. The lab maintains strong connections with the broader Amsterdam Machine Learning ecosystem, including collaborations with ELLIS units in Amsterdam, Delft, and Nijmegen.