Learning Theory Metrics Structure 
Stanford AI Lab Blog
DECEMBER 6, 2021
Kochenderfer Contact : philhc@stanford.edu Links: Paper Keywords : deep learning or neural networks, sparsity and feature selection, variational inference, (application) natural language and text processing Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss Authors : Jeff Z.
The AI Alignment Forum
FEBRUARY 28, 2025
The first of these is the preference structures given by multi-objective RL, where the agent is given multiple reward functions R 1 , R 2 , R 3 , , and has to find a policy that achieves a good trade-off of those rewards according to some specified criterion. This paper is discussed in more detail in this post.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
The AI Alignment Forum
FEBRUARY 7, 2025
Were interested in funding research that leverages knowledge about the structure of a models activation space to efficiently estimate the probability of some particular rare output, even when that probability is too small to estimate by random sampling. Wen et al. , See this section for more details. See this section for more details.
Google Research AI blog
NOVEMBER 28, 2022
A Workshop for Algorithmic Efficiency in Practical Neural Network Training Workshop Organizers include: Zachary Nado , George Dahl , Naman Agarwal , Aakanksha Chowdhery Invited Speakers include: Aakanksha Chowdhery , Priya Goyal Human in the Loop Learning (HiLL) Workshop Organizers include: Fisher Yu, Vittorio Ferrari Invited Speakers include: Dorsa (..)
The AI Alignment Forum
MARCH 28, 2025
And the way you said it just then, it sounded more like the first one: heres a new nice metric of how good your mechanistic explanation is. 00:26:47): And so what this gives us is an interaction metric where we can measure how bad this hypothesis is. Theres a little bit of structure but not very much.
Expert insights. Personalized for you.
40 
Let's personalize your content