Sahel Mohammad Iqbal
Scholar

Sahel Mohammad Iqbal

Google Scholar ID: KP7mJUgAAAAJ
Doctoral Researcher, Aalto University
sequential monte carloreinforcement learningbayesian experimental design
Citations & Impact
All-time
Citations
23
 
H-index
3
 
i10-index
0
 
Publications
8
 
Co-authors
6
list available
Publications
8 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • 1. Paper 'Sequential Monte Carlo for Policy Optimization in Continuous POMDPs' accepted to NeurIPS 2025.
  • 2. Co-author Adrien Corenflos will give a talk on their joint work at MCM 2025.
  • 3. Gave a talk on using particle filters for amortized BED at the Accelerating statistical inference and experimental design with machine learning workshop at the Isaac Newton Institute for Mathematical Sciences.
  • 4. Presented a poster at the Bayesian Decision-making and Uncertainty workshop at NeurIPS 2024 in Vancouver.
  • 5. Published multiple papers, including:
  • - 'Sequential Monte Carlo for policy optimization in continuous POMDPs'
  • - 'Physics-informed machine learning for grade prediction in froth flotation'
  • - 'Recursive nested filtering for efficient amortized Bayesian experimental design'
  • - 'Parallel-in-time probabilistic solutions for time-dependent nonlinear partial differential equations'
  • - 'Nesting particle filters for experimental design in dynamical systems'
Research Experience
  • Working at Aalto University, focusing on Monte Carlo algorithms, reinforcement learning, and Bayesian experimental design.
Education
  • Third-year PhD student at Aalto University, Finland, supervised by Simo Särkkä.
Background
  • Research interests include developing accurate and efficient Monte Carlo algorithms for reinforcement learning and Bayesian experimental design (BED). Recently, also interested in how similar algorithms can be used for inference-time alignment of diffusion and large language models.
Miscellany
  • Outside work, mostly engaged in reading, lifting weights, and writing JAX code. Active projects are available on GitHub.