Γεώργιος Κόλλιας
3 papers in the PaperMetrix corpus
Papers by this author
-
Run Procrustes, Run! On the convergence of accelerated Procrustes Flow.
2018 · arXiv (Cornell University)
In this work, we present theoretical results on the convergence of non-convex accelerated gradient descent in matrix factorization models. The technique is applied to matrix sensing problems with squared loss, for the estimation of a …
-
Quantum Graph Transformers
2023
We propose Quantum Graph Transformers (QGT), a novel approach for realizing the Transformer architecture for graph learning with quantum processors. QGT is built on top of the Graph Trans-former (GT) architecture and addresses the main …
-
Multi-Sense Embeddings for Language Models and Knowledge Distillation
2025 · arXiv (Cornell University)
Transformer-based large language models (LLMs) rely on contextual embeddings which generate different (continuous) representations for the same token depending on its surrounding context. Nonetheless, words and tokens typically have a limited number of senses (or …