Learning latent variable structured prediction models with Gaussian perturbations
Authors: Kevin Bello, Jean Honorio
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We illustrate the method with synthetic experiments and a computer vision application. In this section we illustrate the use of our approach by using the formulation in eq.(6). The goal of the synthetic experiments is to show the improvement in prediction results and runtime of our method. While the goal of the real-world experiment is to show the usability of our method in practice. Synthetic experiments. We present experimental results for directed spanning trees, directed acyclic graphs and cardinality-constrained sets. We performed 30 repetitions of the following procedure. Table 1 shows the runtime, the training distortion as well as the test distortion in an independently generated set of 100 samples. Image matching. We illustrate our approach for image matching on video frames from the Buffy Stickmen dataset... We obtained an average error of 0.3878 (6.98 incorrectly matched keypoints) in the test set... |
| Researcher Affiliation | Academia | Kevin Bello Department of Computer Science Purdue University West Lafayette, IN, USA kbellome@purdue.edu Jean Honorio Department of Computer Science Purdue University West Lafayette, IN, USA jhonorio@purdue.edu |
| Pseudocode | Yes | Algorithm 1 Procedure for sampling a structured output (y , h ) Yx Hx from a greedy local proposal distribution R(w, x) |
| Open Source Code | No | The paper does not provide a link to open-source code for the methodology described, nor does it explicitly state that the code will be made publicly available. |
| Open Datasets | Yes | Image matching. We illustrate our approach for image matching on video frames from the Buffy Stickmen dataset (http://www.robots.ox.ac.uk/~vgg/data/stickmen/). |
| Dataset Splits | No | The paper mentions generating a training set of n=100 samples and splitting the Buffy Stickmen dataset into 120 pairs for training and 67 for testing. However, it does not explicitly state details for a validation split. |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware used for running the experiments (e.g., GPU models, CPU types, memory). |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions, or solver versions) needed to reproduce the experiments. |
| Experiment Setup | Yes | We generated a ground truth parameter w with independent zero-mean and unit-variance Gaussian entries. ... For every pair of possible edges/elements i and j, we define Φij(x, y, h) = 1 (hij xor xij) and i y and j y . ... The latent space H is the set of binary strings with two entries being 1... we define e H (relaxed set) as the set of all binary strings with exactly two entries being 1. ... We considered directed spanning trees of 4 nodes, directed acyclic graphs of 4 nodes and 2 parents per node, and sets of 3 elements chosen from 9 possible elements. ... We used the distortion function and β = 2/3 as prescribed by Claim ii. ... we performed 100 iterations of random inference as in eq.(7). Our mapping Φ(x, y, h) uses SIFT features... |