3 papers
cs.LG2026
Information Geometry of Message Passing
Mykola Lukashchuk, Kyrylo Yemets, Alex Ledbetter +1
We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph. We start from the Bethe free energy and const…
cs.LG2026
Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference
Mykola Lukashchuk, Kyrylo Yemets, Wouter M. Kouw +4
Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be preserved. We identify five facto…
cs.LG2025
GateTS: Versatile and Efficient Forecasting via Attention-Inspired routed Mixture-of-Experts
Kyrylo Yemets, Mykola Lukashchuk, Ivan Izonin
Accurate univariate forecasting remains a pressing need in real-world systems, such as energy markets, hydrology, retail demand, and IoT monitoring, where signals are often intermi…