3 papers
stat.ML2026
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…
stat.ML2026
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…
stat.ML2024
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…