DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies

19 January 2023

Papers citing "DiME: Maximizing Mutual Information by a Difference of Matrix-Based Entropies"

3 / 3 papers shown

Title
Memorization-Compression Cycles Improve Generalization Fangyuan Yu 31 0 0 13 May 2025
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning Md Rifat Arefin G. Subbaraj Nicolas Angelard-Gontier Yann LeCun Irina Rish Ravid Shwartz-Ziv C. Pal LRM 99 0 0 04 Nov 2024
Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training Kun Song Zhiquan Tan Bochao Zou Jiansheng Chen Huimin Ma Weiran Huang 37 0 0 25 Sep 2024