1 citations · 2 across the 4 of their papers we have counts for
5 papers
Mixed-Prior Decision Risk for Open-Set Recognition
L. A. Erlygin, P. D. Proskura, A. A. Zaytsev
In open-set recognition (OSR), a probe must either be identified as one of the known gallery classes or rejected as unknown, so three error types coexist: false acceptance, false r…
ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
Artem Zabolotnyi, Roman Makarov, Mile Mitrovic +4
Uncertainty estimation remains a key challenge when adapting pre-trained language models to downstream classification tasks, with overconfidence often observed for difficult inputs…
Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
Polina Proskura, Alexey Zaytsev
In machine learning, ensembles are important tools for improving the model performance. In natural language processing specifically, ensembles boost the performance of a method due…
Effective training-time stacking for ensembling of deep neural networks
Polina Proscura, Alexey Zaytsev
Ensembling is a popular and effective method for improving machine learning (ML) models. It proves its value not only in classical ML but also for deep learning. Ensembles enhance…
Usage of multiple RTL features for Earthquake prediction
P. Proskura, A. Zaytsev, I. Braslavsky +2
We construct a classification model that predicts if an earthquake with the magnitude above a threshold will take place at a given location in a time range 30-180 days from a given…