• @[email protected]OP
    link
    fedilink
    English
    53 months ago

    We follow the classic experimental paradigm reported in Power et al. (2022) for analyzing “grokking”, a poorly understood phenomenon in which validation accuracy dramatically improves long after the train loss saturates. Unlike the previous templates, this one is more amenable to open-ended empirical analysis (e.g. what conditions grokking occurs) rather than just trying to improve performance metrics

    • @[email protected]
      link
      fedilink
      English
      73 months ago

      Oh okay so they’re just redefining words that are already well-defined so they can make fancy claims.

      • @[email protected]OP
        link
        fedilink
        English
        43 months ago

        Well-defined for casual use is very different than well-defined for scholarly research. It’s standard practice to take colloquial vocab and more narrowly define it for use within a scientific discipline. Sometimes different disciplines will narrowly define the same word two different ways, which makes interdisciplinary communication pretty funny.

        • @[email protected]
          link
          fedilink
          English
          43 months ago

          It’s standard practice to take colloquial vocab and more narrowly define it for use within a scientific discipline.

          No. It’s not standard at all, especially when the goal is overtly misleading.

          Sometimes different disciplines will narrowly define the same word two different ways

          Maybe one or both disciplines is promoting bullshit.