Scalable Semidefinite Relaxation for Maximum A Posterior Estimation

Authors: Qixing Huang, Yuxin Chen, Leonidas Guibas

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have evaluated the performance of SDR on various benchmark datasets including OPENGM2 and PIC in terms of boththe quality of the solutions and computation time. Experimental results demonstrate that for a broad class of problems, SDPAD-LR outperforms state-of-the-art algorithms in producing better MAP assignments in an efficient manner.
Researcher Affiliation Academia Qixing Huang HUANGQX@STANFORD.EDU Department of Computer Science, Stanford University, Stanford, CA 94305, USA Yuxin Chen YXCHEN@STANFORD.EDU Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA Leonidas Guibas GUIBAS@CS.STANFORD.EDU Department of Computer Science, Stanford University, Stanford, CA 94305 USA
Pseudocode Yes Algorithm 1 SDPAD for solving SDR; Algorithm 2 SDPAD-LR for solving SDR
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the methodology is openly available.
Open Datasets Yes We have evaluated SDPAD-LR on two collections of benchmark datasets: OPENGM2 (Kappes et al., 2013a) and a probabilistic inference challenge (PIC, 2011), and a new data set ORIENT for the task of estimating consistent camera orientations (Crandall et al., 2011).
Dataset Splits No The paper mentions evaluating performance on benchmark datasets but does not specify training, validation, or test splits with percentages or counts for reproducibility. It implicitly uses predefined splits from the benchmarks if available, but doesn't state them explicitly.
Hardware Specification No The paper mentions running experiments "On a standard PC" or "on a regular PC" but does not provide specific hardware details such as CPU/GPU models, memory, or processor speeds.
Software Dependencies No The paper mentions "preliminary Matlab implementation" but does not specify any software names with version numbers for libraries, solvers, or other dependencies required to replicate the experiments.
Experiment Setup Yes input: kmax = 1000, ϵ = 10 4, µmin = 10 3, ρ = 1.005.; input: kmax = 5000, ϵ = 10 4, µmin = 10 3, ρ = 1.005, δ = 1e 2, rmax = 32, r = 4.; Specifically, after each round of SDPAD-LR, we fix the optimal state j of a variable xi if xi,j > tmax (tmax = 0.99 for all the examples) or xi,j = max1 i n,1 j m xi,j.