2 papers
cs.LG2026
Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems
Alankrita Bhatt, Mukur Gupta, Germain Kolossov +1
Generating data from discrete distributions is important for a number of application domains including text, tabular data, and genomic data. Several groups have recently used rando…
stat.ML2023
Towards a statistical theory of data selection under weak supervision
Germain Kolossov, Andrea Montanari, Pulkit Tandon
Given a sample of size , it is often useful to select a subsample of smaller size to be used for statistical estimation or learning. Such a data selection step is useful t…