AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

Huikang Liu, Xiao Li, Anthony Man-Cho So

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Determinantal point process inference · 3 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use smaller decay factor gamma (e.g. 0.7 instead of 0.95) (ablation)ReSync · Synthetic SO(3), n=400-1000convergence speedMixed
increase number of nodes n (ablation)ReSync · Synthetic SO(3)convergenceImproved
add additive noise sigma = 1ReSync vs baselines · Synthetic SO(3), n=200recovery errorImproved
noise-free case, compare ReSync to robust baselinesReSync · Synthetic SO(3), n=200recovery errorNo clear effect
use ReSync instead of LUD and DESCReSync · Lucy datasetresidualsImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy