Non-Gaussian Gaussian Processes for Few-Shot Regression
Authors: Marcin Sendera, Jacek Tabor, Aleksandra Nowak, Andrzej Bedychaj, Massimiliano Patacchiola, Tomasz Trzcinski, Przemysław Spurek, Maciej Zieba
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically tested the flexibility of NGGPs on various few-shot learning regression datasets, showing that the mapping can incorporate context embedding information to model different noise levels for periodic functions. In this section, we provide an extensive evaluation of our approach (NGGP) on a set of challenging few-shot regression tasks. We compare the results with other baseline methods used in this domain. As quantitative measures, we use the standard mean squared error (MSE) and, when applicable, the negative log-likelihood (NLL). |
| Researcher Affiliation | Academia | Marcin Sendera Jagiellonian University Jacek Tabor Jagiellonian University Aleksandra Nowak Jagiellonian University Andrzej Bedychaj Jagiellonian University Massimiliano Patacchiola University of Cambridge Tomasz Trzcinski Jagiellonian University, Warsaw University of Technology, Przemysław Spurek Jagiellonian University Maciej Zieba Wrocław University of Science and Technology, |
| Pseudocode | Yes | Algorithm 1 NGGP in the few-shot setting, train and test functions. |
| Open Source Code | Yes | the code is released with an open-source license2. 2https://github.com/gmum/non-gaussian-gaussian-processes |
| Open Datasets | Yes | Sines dataset We start by comparing NGGP to other few-shot learning algorithms in a simple regression task defined on sines functions. To this end, we adapt the dataset from [9]... Head-pose trajectory In this experiment, we use the Queen Mary University of London multiview face dataset [13]... Object pose prediction We also study the behavior of NGGP in a pose prediction dataset introduced in [54]... The tasks are created by selecting an object from the Pascal 3D [51] dataset... Power Dataset In this series of experiments, we use the Power [1] dataset... NASDAQ and EEG datasets In order to test the performance of our methods for real-world time series prediction, we used two datasets NASDAQ100 [30] and EEG [8]. |
| Dataset Splits | Yes | We train the model using the tasks from the first 50 days, randomly sampling 10 points per task, while validation tasks are generated by randomly selecting from the following 50 days. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. The self-assessment section states 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [No]'. |
| Software Dependencies | No | The paper mentions using specific models like Ffjord [16] but does not provide specific software dependencies with version numbers (e.g., Python version, library versions like PyTorch, TensorFlow, scikit-learn, etc.). |
| Experiment Setup | No | For more information about the training regime and architecture, refer to Supplementary Materials A. Information about architecture and training regime is given in Supplementary Materials A. |