AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm

Yasunori Akagi, Naoki Marumo, Hideaki Kim, Takeshi Kurashima, Hiroyuki Toda

NeurIPS 2021 · Learning theory and algorithms › Combinatorial and search optimization · approach: Globally optimal geometric optimization · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
Replace approximate relaxed inference with exact integer-valued DCA inferenceCGM MAP inference on path graphs · Synthetic instances, uniform and distance potentials; small populationobjective function: -7.19e+01 -> -9.97e+01; 3.20e+01 -> 3.35e-01Improved
Replace approximate relaxed inference with exact integer-valued DCA inferenceCGM MAP inference on path graphs · Real-world car trajectories, M=10^1, R=56 and R=208objective function: 2.76e+02 -> 2.30e+00; 3.83e+02 -> 2.30e+00Improved
Use the left-endpoint slope rather than the midpoint slope for the surrogate (ablation)Proposed DCA · Synthetic instancesobjective function: -9.81e+01 -> -9.97e+01Improved
Use the left-endpoint slope rather than the right-endpoint slope for the surrogate (ablation)Proposed DCA · Synthetic instancesobjective function: -9.64e+01 -> -9.97e+01Improved
Use the midpoint slope rather than the right-endpoint slope for the surrogate (ablation)Proposed DCA · Synthetic, distance potential (M=10^1, R=10)objective function: 3.35e-01 -> 3.35e-01No clear effect
Use exact integer-valued inference instead of continuous relaxationCGM MAP inference on path graphs · Synthetic instances (R=20, M=10^2)sparsity: 0% -> 76%; 0% -> 83%Improved

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