Reposted by School of Computer Science, University of Sydney
I am recruiting PhD students for my group at Sydney!
Apply by Oct 31
If you are a student: please consider applying
If you are an academic: please share with students
I have funding and flexibility in topic. If you are at COLM, let's chat! Details:
jkk.name/students/rec...
jkk.name
Recruiting: PhD
Work with me on NLP at the University of Sydney!
Please apply by October 31st.
I will be interviewing and making offers in November. I encourage students who I make offers to to apply for a university...
![Title: Entropy Equivalence Testing
Abstract: We introduce the problem of entropy equivalence testing for probability distributions, a relaxation of the well-studied closeness testing problem, where the distribution testing algorithm is now only required to distinguish, given samples from two unknown distributions p,q and a parameter ε∈(0,1/2], between p=q and |H(p)−H(q)|⩾ε (where H denotes the Shannon entropy). We provide a time- and sample-efficient algorithm for this task, showing that the optimal sample complexity for this task can be significantly lower than that of closeness testing. As an application, we leverage this result to provide the first non-trivial testing algorithm for (standard) closeness of low-degree Bayesian networks, which significantly improves on either the sample or time complexity of a baseline based on full learning.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:iuogym7jtbioyaq32ecf6aln/bafkreici33q52fcvybzs2nlwke7bprnbafvxc447u5kbxotkfb4u37mvye)
