Estimating the Unique Information of Continuous Variables
Authors: Ari Pakman, Amin Nejatbakhsh, Dar Gilboa, Abdullah Makkeh, Luca Mazzucato, Michael Wibral, Elad Schneidman
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We obtain excellent agreement with known analytic results for Gaussians, and illustrate the power of our new approach in several brain-inspired neural models. Our method is capable of recovering the effective connectivity of a chaotic network of rate neurons, and uncovers a complex trade-off between redundancy, synergy and unique information in recurrent networks trained to solve a generalized XOR task. |
| Researcher Affiliation | Academia | Ari Pakman Columbia University Amin Nejatbakhsh Columbia University Dar Gilboa Harvard University Abdullah Makkeh Georg August University Luca Mazzucato University of Oregon Michael Wibral Georg August University Elad Schneidman Weizmann Institute |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | No | The paper describes using simulated data and input drawn from a Gaussian Mixture Model, e.g., 'The results, presented in Figure 2. are obtained from 3000 samples from each model' and 'Input data drawn from a 2D Gaussian Mixture Model with K mixture components'. It does not provide concrete access information for a publicly available dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, or citations to predefined splits) needed to reproduce the data partitioning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types) used for running its experiments. |
| Software Dependencies | No | The paper mentions software packages like 'pyvinecopulib python package [43]' and 'IDTxl [58]' but does not provide specific version numbers for these or other software dependencies. |
| Experiment Setup | Yes | In this and the rest of the experiments, we optimized the parameters (θ, φ) using the ADAM algorithm [47] with a fixed learning rate 10 2 during 1200 iterations, and using A = 50. |