Session: Efficient Optimization Methods for LLMs (Part I)
Chair: Ruoyu Sun
Cluster: Optimization for Emerging Technologies (LLMs, Quantum Computing, ...)
Talk 1: Adam-mini: Use Fewer Learning Rates To Gain More
Speaker: Ruoyu Sun
Abstract: TBD
Talk 2: GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Speaker: Zhangyang Wang
Abstract: TBD
Talk 3: LoRA-GA: Low-Rank Adaptation with Gradient Approximation
Speaker: Jian Li
Abstract: TBD
