Nicholas Barnfield

According to our database, Nicholas Barnfield authored at least 7 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval.

Nicholas Barnfield, Juno Kim, Eshaan Nichani, Jason D. Lee, Yue M. Lu

CoRR, May, 2026

A Scale-Shape Dual Newton Method for Entropic Least Squares.

Nicholas Barnfield, James V. Burke, Michael P. Friedlander, Tim Hoheisel

CoRR, April, 2026

Multi-layer Cross-Attention is Provably Optimal for Multi-modal In-context Learning.

Nicholas Barnfield, Subhabrata Sen, Pragya Sur

CoRR, February, 2026

2025

High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification.

Nicholas Barnfield, Hugo Cui, Yue M. Lu

CoRR, September, 2025

2024

Ziv-Merhav Estimation for Hidden-Markov Processes.

Nicholas Barnfield, Raphaël Grondin, Gaia Pozzoli, Renaud Raquépas

Proceedings of the IEEE International Symposium on Information Theory, 2024

2023

On the Ziv-Merhav theorem beyond Markovianity II: A thermodynamic approach.

Nicholas Barnfield, Raphaël Grondin, Gaia Pozzoli, Renaud Raquépas

CoRR, 2023

On the Ziv-Merhav theorem beyond Markovianity.

Nicholas Barnfield, Raphaël Grondin, Gaia Pozzoli, Renaud Raquépas

CoRR, 2023