Reproduce “Adversarially Robust Topological Inference” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Siddharth Vishwanath, Bharath K. Sriperumbudur, Kenji Fukumizu, Satoshi Kuriki
The authors introduce MoM Dist, which partitions observations into blocks and estimates a query point’s distance using the median of its distances to those blocks. These distances weight a filtration, reducing sensitivity to corrupted groups when the block count exceeds twice the outlier count. Under stated assumptions, its bottleneck error is near minimax, with a logarithmic-factor gap, not universal recovery.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.