• f_devd an hour ago

    Having worked on compression algos, any NN is just way to slow for (de-)compression. A potential usage of them is for coarse prior estimation in something like rANS, but even then the overhead cost would need to carefully weighted against something like Markov chains since the relative cost is just so large.

    • msephton 11 hours ago

      No mention of decompression speed and validation, or did I miss something?

      • savalione 11 hours ago

        It's in the post: Benchmarks -> Speed

        tl;dr: SMLL is approximately 10,000x slower than Gzip