[1903.03129] SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systemshttps://arxiv.org/abs/1903.03129
An interesting approach to a deep learning problem. Instead of computing everything as matrix multiplication (which generally requires a GPU for throughput), turn it into a sparse lookup table and use a conventional CPU.
I'm not sure I understand the paper well enough to comment on the methodology, but fast inference and training on conventional CPUs would be very exciting - building and running GPU based stacks is fiddly and time consuming whereas the CPU is there and just works. CPUs are also great for scaling down!
Related By Tags
- 🔗 Get Started · Snorkel
- 🔗 LabGopher :: Great server deals on eBay
- 🔗 [2005.03220] Fractional ridge regression: a fast, interpretable reparameterization of ridge regression
- 🔗 Straight to Spam
- 🔗 Getting machine learning to production · Vicki Boykis
- 🔗 Eye-catching advances in some AI fields are not real | Science | AAAS
- 🔗 Large image datasets: A pyrrhic win for computer vision? | OpenReview
- 🔗 Disembodied Machine Learning: On the Illusion of Objectivity in NLP | OpenReview
- 🔗 Full Stack Deep Learning - Full Stack Deep Learning
- 🔗 Scalability! But at what COST?