Bounded Regret
  • Home

Forecasting ML Benchmarks in 2023

4 years ago 15 min read
Thanks to Collin Burns, Ruiqi Zhong, Cassidy Laidlaw, Jean-Stanislas Denain, and Erik Jones, who generated most of the considerations discussed in this post. Previously [https://bounded-regret.ghost.io/ai-forecasting-one-
Read Now Read Later
Jacob Steinhardt
By: Jacob Steinhardt

AI Forecasting: One Year In

4 years ago 7 min read
Last August, my research group created a forecasting contest [https://bounded-regret.ghost.io/ai-forecasting/] to predict AI progress on four benchmarks. Forecasts were asked to predict state-of-the-art performance
Read Now Read Later
Jacob Steinhardt
By: Jacob Steinhardt

How fast can we perform a forward pass?

4 years ago 18 min read
Thanks to Hao Zhang, Kayvon Fatahalian, and Jean-Stanislas Denain for helpful discussions and comments. Addendum and erratum. See here [https://kipp.ly/blog/transformer-inference-arithmetic/] for an excellent discussion of similar
Read Now Read Later
Jacob Steinhardt
By: Jacob Steinhardt

Early 2022 Paper Round-up (Part 2)

4 years ago 6 min read
Last week [https://bounded-regret.ghost.io/early-2022-paper-round-up/], I talked about six recent papers from our group, and discussed the first two in detail. This week, I'll
Read Now Read Later
Jacob Steinhardt
By: Jacob Steinhardt

Early 2022 Paper Round-up

4 years ago 4 min read
My students and collaborators have been doing some particularly awesome work over the past several months, and to highlight that I wanted to summarize their papers here, and explain why I’m excited
Read Now Read Later
Jacob Steinhardt
By: Jacob Steinhardt
Newer Posts
Page 4 of 18
Older Posts
Powered by Ghost
Bounded Regret