Alexander Nikitin

Trustworthy AI
Machine Learning for Health Group @ Aalto University
Finnish Center for Artificial Intelligence

Email: firstname.lastname(at)aalto.fi
GitHub: @AlexanderVNikitin
Twitter: @NikitinAlexV
Blog: Medium


Status

I specialize in machine learning and probabilistic methods with a focus on trustworthiness. In particular, I am interested in generative models, uncertainty quantification, time series, and graphs. My research is driven by real-world problems in predictive maintenance, biology, and healthcare.

Selected Publications

Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen. Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities. NeurIPS'24.
Preprint | Code

Alexander Nikitin, Letizia Iannucci, Samuel Kaski. TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series. NeurIPS'24.
Preprint | Code

Sergio Hernández-Gutiérrez, Minttu Alakuijala, Alexander Nikitin, Pekka Marttinen. Recursive Decomposition with Dependencies for Generic Divide-and-Conquer Reasoning. Workshop on System-2 Reasoning at Scale @ NeurIPS'24.

Daniel Augusto de Souza, Alexander Nikitin, S. T. John, Magnus Ross, Mauricio A. Álvarez, Marc Peter Deisenroth, João P. P. Gomes, Diego Mesquita, and César Lincoln Mattos. Thin and Deep Gaussian Processes. NeurIPS'23.
Preprint | Code

Alexander Nikitin and Samuel Kaski. Human-in-the-Loop Large-Scale Predictive Maintenance of Workstations. KDD'22.
Preprint | ACM | Poster | Presentation

Alexander Nikitin, Ti John, Arno Solin, and Samuel Kaski. Non-separable spatio-temporal graph kernels via SPDEs. AISTATS'22.
Preprint | PMLR | Poster | Code

Alexander Nikitin and Samuel Kaski. Decision Rule Elicitation for Domain Adaptation. IUI'21.
Preprint | ACM

Open Source

Time Series Generative Modeling (TSGM). GitHub
TopoNetX (contributor). GitHub

Talks

Graph kernels via SPDE framework, BayesComp 2023. Slides

Patents

My research has resulted in several granted patents, e.g., FI130615B, FI130697B1, and FI130073B.

Teaching

Seminar on Large Language Models (2023-...), Aalto University,
Machine Learning: Advanced Probabilistic Mehtods (2021-...), TA, Aalto University,
Bayesian Data Analysis: Global South (2021), TA, Aalto University,
Principles of Algorithmic Techniques (2020), TA, Aalto University.

Community Service

I am a reviewer for NeurIPS, ICML, ICLR, EMNLP, and other ML and data mining conferences and journals.