6 papers
Recovering manifold structure in LLM responses through a joint Euclidean mirror
Maximilian Baum, Aranyak Acharyya, Tianyi Chen +5
Understanding the behavior of black-box large language models and determining effective means of comparing their performance is a key task in modern machine learning. We consider h…
Vertex misalignment and changepoint localization in network time series
Tianyi Chen, Mohammad Sharifi Kiasari, Sijing Yu +5
Inference for time series of networks often relies on accurate vertex correspondence between network realizations at different times. In practice, however, such vertex alignments c…
Gaussian mixture models as a proxy for interacting language models
Edward L. Wang, Mohammad Sharifi Kiasari, Tianyu Wang +4
Large language models (LLMs) are powerful tools that, in a number of settings, overlap with the results of human pattern recognition and reasoning. Retrieval-augmented generation (…
Euclidean mirrors and first-order changepoints in network time series
Tianyi Chen, Zachary Lubberts, Avanti Athreya +2
We describe a model for a network time series whose evolution is governed by an underlying stochastic process, known as the latent position process, in which network evolution can…
Dynamic networks clustering via mirror distance
Runbing Zheng, Avanti Athreya, Marta Zlatic +2
The classification of different patterns of network evolution, for example in brain connectomes or social networks, is a key problem in network inference and modern data science. B…
Procrustes Problems on Random Matrices
Hajg Jasa, Ronny Bergmann, Christian Kümmerle +2
Meaningful comparison between sets of observations often necessitates alignment or registration between them, and the resulting optimization problems range in complexity from those…