This package contains the Matlab implementation the COAF algorithm and 3 baselines in the paper draft "Latency-Aware Contextual Bandit: Application to Cryo-EM Data Collection" submitted to ICLR 2026.


# The Environments

MATLAB 2023b. Other versions should also work.


# Experiments

Figure 2(a): run "movielens_threshold.m"

Figure 2(b): run "movielens_coaf_orc.m"

Figure 2(c): run "movielens_coaf_TS.m"

Figure 2(d): run "movielens_coaf.m"


# Dataset

The MovieLens 1M Dataset is stored in file "movielens.mat" under variable "ratings". The file also contains a matrix completion result stored in variable "ratings_r" of the MovieLens 1M Datase using method developed in [2]. 

[1] Harper, F. Maxwell, and Joseph A. Konstan. "The movielens datasets: History and context." Acm transactions on interactive intelligent systems (tiis) 5.4 (2015): 1-19.

[2] Nie, Feiping, Heng Huang, and Chris Ding. "Low-rank matrix recovery via efficient schatten p-norm minimization." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 26. No. 1. 2012.