Abstract:Reducing power consumption in AI accelerators is increasingly important. Approximate computing can reduce power consumption while keeping the accuracy loss small. Since multipliers are power-hungry components in AI models, this paper focuses on synthesizing low-power approximate multipliers (AxMs). Unlike prior works that design AxMs separately from AI model training, we present TRAM, which jointly optimizes the AxM structure and AI model parameters to lower power with small accuracy loss. Experiments show that compared to state-of-the-art AxMs, TRAM achieves up to 25.05% AxM power reduction on CNNs with CIFAR-10, and reduces power by up to 27.09% on vision transformers with ImageNet.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR) |
| Cite as: | arXiv:2605.08231 [cs.LG] |
| (or arXiv:2605.08231v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08231 arXiv-issued DOI via DataCite |
Submission history
From: Chang Meng [view email]
[v1]
Wed, 6 May 2026 20:39:32 UTC (314 KB)