Alisa Sheinkman
PhD candidate at the University of Edinburgh.
I am a PhD researcher working under the supervision of Sara Wade. I aim to develop advances in Bayesian deep modelling. Namely, I study efficient inference schemes with a focus on scalable variational inference algorithms such as stochastic and black box variational inference; My work addresses the challenge of architecture specification of Bayesian neural networks, Bayesian model choice and model combination in the realms of big data and overparametrized deep models.
Passed my viva (minor corrections)! May 2025, Worldwide
Publications
SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era, E. Semenova, A. Sheinkman, T. J. Hitge, S.M. Hall, J. Cockayne, arXiv:2502.06753, 2025.
Understanding the Trade-offs in Accuracy and Uncertainty Quantification: Architecture and Inference Choices in Bayesian Neural Networks, A. Sheinkman, S. Wade, in Proceedings of the ECML PKDD, 2025 (to appear). Corresponding code.
Variational Bayesian Bow tie Neural Networks with Shrinkage, A. Sheinkman, S. Wade, arXiv:2411.11132, 2024. Corresponding code.
Deep learning techniques for noise annoyance detection: results from an intensive workshop at the alan turing institute, A. Mitchell, E. Brown, R. Deo, Y. Hou, J. Kirton-Wingate, J. Liang, A. Sheinkman, C. Soelistyo, H. Sood, and A. Wongprommoon The Journal of the Acoustical Society of America, 153(3_supplement): A262-A262, 2023.