Homepage
Close
Menu

Site Navigation

  • Home
  • Archive(TODO)
    • By Day
    • By Month
  • About(TODO)
  • Stats
Close
by zacharylipton on 2019-12-06 (UTC).

The double descent phenomenon is described in ~1000 papers & talks over past year. It's featured in at least 1 slide per talk @ last summer's Simons workshop on Foundations of DL. Why is this @OpenAI post getting so much attention as if it's a new discovery? Am I missing smtg? https://t.co/DvNqAGlKWm

— Zachary Lipton (@zacharylipton) December 6, 2019
research
by hardmaru on 2019-12-06 (UTC).

Deep Double Descent: Where Bigger Models and More Data Hurt

They conduct an empirical study of the ‘double descent’ phenomenon in neural nets, and investigate this behavior in a range of architectures and its relationship to model size and training time.https://t.co/C9RfiRLlO4 pic.twitter.com/GnLyaExkQ1

— hardmaru (@hardmaru) December 6, 2019
research

Tags

learning tutorial misc nlp rstats gan ethics research dataviz survey python tool security kaggle video thought bayesian humour tensorflow w_code bias dataset pytorch cv tip application javascript forecast swift golang rl jax julia gnn causal surey diffusion
© Copyright Philosophy 2018 Site Template by Colorlib