Monarch: Expressive Structured Matrices for Efficient and Accurate Training
Tri Dao, Beidi Chen, Nimit Sohoni, Arjun Desai, Michael Poli, Jessica Grogan, Alexander Liu, Aniruddh Rao, Atri Rudra, Christopher Ré
Abstract
Large neural networks excel in many domains, but they are expensive to train and fine-tune. A popular approach to reduce their compute or memory requirements is to replace dense weight matrices with structured ones (e.g., sparse, low-rank, Fourier transform). These methods have not seen widespread adoption (1) in end-to-end training due to unfavorable efficiency--quality tradeoffs, and (2) in dense-to-sparse fine-tuning due to lack of tractable algorithms to approximate a given dense weight matrix. To address these issues, we propose a class of matrices (Monarch) that is hardware-efficient (they are parameterized as products of two block-diagonal matrices for better hardware utilization) and expressive (they can represent many commonly used transforms). Surprisingly, the problem of approximating a dense weight matrix with a Monarch matrix, though nonconvex, has an analytical optimal solution. These properties of Monarch matrices unlock new ways to train and fine-tune sparse and dense models. We empirically validate that Monarch can achieve favorable accuracy-efficiency tradeoffs in several end-to-end sparse training applications: speeding up ViT and GPT-2 training on ImageNet classification and Wikitext-103 language modeling by 2x with comparable model quality, and reducing the error on PDE solving and MRI reconstruction tasks by 40%. In sparse-to-dense training, with a simple technique called "reverse sparsification," Monarch matrices serve as a useful intermediate representation to speed up GPT-2 pretraining on OpenWebText by 2x without quality drop. The same technique brings 23% faster BERT pretraining than even the very optimized implementation from Nvidia that set the MLPerf 1.1 record. In dense-to-sparse fine-tuning, as a proof-of-concept, our Monarch approximation algorithm speeds up BERT fine-tuning on GLUE by 1.7x with comparable accuracy.
Create a lesson
Related papers
Causal Concept Explanations for Deep Neural Models
Josh Rountree, Pulkit Verma, Oswin So et al.
Discovering Equations for the Thermodynamics of South Asian Monsoon Precipitation
Savannah L. Ferretti, Jane W. Baldwin, Michael S. Pritchard et al.
REAL Loss: Optimizing Real Expected Acceptance Length for Speculative Decoding
Yu Tian
A Margin Perspective on LoRA: Robustness to Catastrophic Forgetting and Adapter Merging (MaLoRA)
Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald et al.
Uncertainty-Aware Hybrid Offline Reinforcement Learning with Online Action Selection Enabled by Sparse Gaussian-Process Critics
Marco Chan, Christos Evripidou, Liqiu Dong et al.
The Unused Input: The Initial State as a Conditioning Interface for Recurrent TSFMs
Bernhard Voggenberger, Christian Ganhör, Levente Zólyomi et al.