Stas Syrota — accepted AI-conference papers

2025

Identifying Metric Structures of Deep Latent Variable Models

Stas Syrota, Yevgen Zainchkovskyy, Johnny Xi, Benjamin Bloem-Reddy, Søren Hauberg

ICML 2025poster

Deep latent variable models learn condensed representations of data that, hopefully, reflect the inner workings of the studied phenomena. Unfortunately, these latent representations are not statistically identifiable, meaning they cannot be uniquely determined. Domain experts, therefore, need to tre…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

VIKING: Deep variational inference with stochastic projections

Samuel G. Fadel, Hrittik Roy, Nicholas Krämer, Yevgen Zainchkovskyy, Stas Syrota, Alejandro Valverde Mahou +2

NeurIPS 2025poster

Variational mean field approximations tend to struggle with contemporary overparametrized deep neural networks. Where a Bayesian treatment is usually associated with high-quality predictions and uncertainties, the practical reality has been the opposite, with unstable training, poor predictive power…

Cited by 0 Source ↗Scholar ↗