1 citations · 2 across the 5 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Emergent Capabilities Arise Randomly from Learning Sparse Attention Patterns
Vatsal Baherwani, Zixi Chen, Shikai Qiu +2
Neural scaling laws for transformer language models predict smooth improvements in pretraining loss with increasing parameters, but downstream capabilities such as in-context learn…
cs.LG2026
Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales
Shikai Qiu, Zixi Chen, Hoang Phan +2
Several recently introduced deep learning optimizers utilizing matrix-level preconditioning have shown promising speedups relative to the current dominant optimizer AdamW, particul…
cs.LG2024★ 1 cited
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
Andres Potapczynski, Shikai Qiu, Marc Finzi +6
Dense linear layers are the dominant computational bottleneck in large neural networks, presenting a critical need for more efficient alternatives. Previous efforts focused on a sm…