4 papers
A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond
Nikos Tsikouras, Yorgos Pantis, Ioannis Mitliagkas +1
Understanding the dynamics of feature learning in neural networks (NNs) remains a significant challenge. The work of (Mousavi-Hosseini et al., 2023) analyzes a multiple index teach…
MaxSketch: Robust Distinct Counting in Streams via Random Projections
Nikos Tsikouras, Constantine Caramanis, Christos Tzamos
Estimating the number of distinct elements in a data stream is well understood when repeated elements are identical. In modern settings, however, observations are high-dimensional…
Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
Panagiotis Giannoulis, Yorgos Pantis, Christos Tzamos
Despite their proficiency in various language tasks, Large Language Models (LLMs) struggle with combinatorial problems like Satisfiability, Traveling Salesman Problem, or even basi…
Optimization Can Learn Johnson Lindenstrauss Embeddings
Nikos Tsikouras, Constantine Caramanis, Christos Tzamos
Embeddings play a pivotal role across various disciplines, offering compact representations of complex data structures. Randomized methods like Johnson-Lindenstrauss (JL) provide s…