Literature review on energy measurement of compressed DL models (and a cs.LG endorsement ask)

An independent researcher with a B.Sc. in CSE from Rangamati Science and Technology University in Bangladesh published a literature review of 53 works spanning 2019-2026 finding that software energy estimators and hardware counters such as RAPL and NVML disagree by margins comparable to the savings that quantization, pruning, and distillation claim to deliver. The review, posted to Zenodo under DOI 10.5281/zenodo.22842954 with data and tables on GitHub, also reports that FLOPs correlate weakly with measured energy once memory bandwidth, batch size, and backend kernel realization are accounted for, and that compression rankings on one hardware platform do not reliably transfer to another. The author is seeking a cs.LG endorsement from an active arXiv author to post the review and a related Master's research proposal.

Hi all, I’m an independent researcher B.Sc. CSE, Rangamati Science and Technology University, Bangladesh and just finished a literature review on a question that seemed under-examined: does model compression quantization, pruning, distillation actually reduce measured energy, or just FLOPs? Drawing on a corpus of 53 works 2019-2026 , the review finds a few things that surprised me. Software energy estimators and hardware counters RAPL, NVML disagree by margins comparable to the savings compression claims to deliver. FLOPs correlate weakly with measured energy once memory bandwidth, batch size, and backend kernel realization are accounted for. And compression rankings on one hardware platform don’t reliably transfer to another. Zenodo DOI : Energy Measurement of Compressed Deep Learning Models: A Literature Review | Zenodo https://doi.org/10.5281/zenodo.22842954 Data/tables repo: GitHub - ShohanRony/energy-measurement-compressed-dl-review: Literature review: energy measurement of compressed deep learning models · GitHub https://github.com/ShohanRony/energy-measurement-compressed-dl-review Separately, I’d appreciate any pointers from this community. I’m a first-time arXiv submitter and need a cs.LG endorsement to post this and a related Master’s research proposal there. If you’re an active cs.LG author on arXiv and this area is anywhere near your work, I’d be glad to share more detail, feel free to reply or DM. Happy to hear feedback on the review itself too, especially if I’ve missed relevant work. Thanks for reading