Prakhar Verma

I am a machine learning Ph.D. student with Arno Solin's research group at Aalto University, Finland. I am broadly interested in probabilistic modeling and efficient inference techniques. For my master’s thesis, I researched on developing variational inference techniques for non-linear SDEs. Recently, my work has focused on sequential decision-making models that need computationally efficient and well-calibrated uncertainty.

I graduated from Aalto University, Finland, with a Master's in Machine Learning, Data Science and Artificial Intelligence as major and Mathematics as minor (2019-2021).

In 2021-2022, alongside Aalto University, I also worked with SpectacularAI as a consultant for an electronics firm developing methods to integrate uncertainty in their deep learning models, making them robust. During 2016-2019, I worked in the R&D team of TomTom, responsible for devising, developing, and bringing into production innovative new technologies. My work mainly revolved around machine learning, image processing, and automation, focusing on revolutionizing map data.

Email  /  CV  /  Github  /  LinkedIn


  • [March 2023] Prakhar Verma , Vincent Adam, Arno Solin. Gaussian Variational Inference for Diffusion Processes Revisited accepted as a poster in "BayesComp" 2023. Poster
  • [November 2022] Prakhar Verma, Paul Chang, Arno Solin, Mohammad Emtiyaz Khan. Sequential Learning in GPs with Memory and Bayesian Leverage Score accepted in Asian Conference in Machine Learning (ACML) workshop "Continual Lifelong Learning" 2022 (Contributed talk). Link   Slide
  • [October 2022] Paul Chang, Prakhar Verma, ST John, Victor Picheny, Henry Moss, Arno Solin. Fantasizing with Dual GPs in Bayesian Optimization and Active Learning accepted in NeurIPS workshop "Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems" 2022. Link   Poster
  • [August 2022] Started as a Doctoral Researcher with Prof. Arno Solin at Aalto University, Finland.
  • [October 2021] Prakhar Verma, Vincent Adam, Arno Solin. Sparse Gaussian Processes for Stochastic Differential Equations accepted in NeurIPS workshop "The Symbiosis of Deep Learning and Differential Equations" 2021. Link   Poster
  • [October 2021] Arno Solin, Ella Tamir, Prakhar Verma. Scalable Inference in SDEs by Direct Matching of the Fokker–Planck–Kolmogorov Equation accepted in NeurIPS 2021. Link  Poster
  • [July 2021] Successfully submitted M.Sc. thesis titled "Sparse Gaussian processes for stochastic differential equations" under Dr Vincent Adam and Prof. Arno Solin.


Prakhar Verma (2021). Sparse Gaussian processes for stochastic differential equations. Master’s thesis. Aalto University. PDF

Prakhar Verma (2016). Development of automated GIS Tools on various platforms. Bachelor's thesis. Uttarakhand Technical University, TomTom India. PDF