Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

No. From my link:

>Additionally, we provide strong counterexamples to two recently proposed theories that models learned through pruning techniques can be trained from scratch to the same test set performance of a model learned with sparsification as part of the optimization process. Our results highlight the need for large-scale benchmarks in sparsification and model compression.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: