block coordinate descent

2 papers across 2 sessions

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

#701 · Yuxi Liu, Renjia Deng, Yutong He, xue wang, Tao Yao, Kun Yuan

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Block Coordinate Descent for Neural Networks Provably Finds Global Minima

#3200 · Shunta Akiyama

This paper proves that a block coordinate descent algorithm can train deep neural networks to global minima under certain activation functions, extending to ReLU via architectural modifications.