Towards Sample-efficient Overparameterized Meta-learning
Authors: Yue Sun, Adhyyan Narang, Ibrahim Gulluk, Samet Oymak, Maryam Fazel
NeurIPS 2021 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Numerical experiments on real and synthetic data verify our insights on overparameterized meta-learning. |
| Researcher Affiliation | Academia | Yue Sun University of Washington EMAIL Adhyyan Narang University of Washington EMAIL Halil Ibrahim Gulluk Bogazici University EMAIL Samet Oymak University of California, Riverside EMAIL Maryam Fazel University of Washington EMAIL |
| Pseudocode | Yes | Algorithm 1 Constructing the optimal representation |
| Open Source Code | Yes | The code for this paper is in https://github.com/sunyue93/Rep-Learning. |
| Open Datasets | Yes | A Res Net-50 network pretrained on Imagenet was utilized to obtain a representation of R features for classification on CIFAR-10. |
| Dataset Splits | Yes | Data for Representation Learning (Phase 1). We have T tasks, each with n1 training examples... Data for Few-Shot Learning (Phase 2). Few-shot dataset has n2 examples (yi, xi)n2 j=1 i.i.d. Dβ. In Figure 1(a), 'Few shot train size = 20 Few shot train size = 100 Few shot train size = 500' are explicitly given. |
| Hardware Specification | No | The paper states '[N/A]' for question 3(d) regarding the total amount of compute and type of resources used for experiments, indicating no hardware specifications are provided. |
| Software Dependencies | No | The paper mentions software components like 'Res Net-50 network' but does not specify any software dependencies with version numbers. |
| Experiment Setup | Yes | A Res Net-50 network pretrained on Imagenet was utilized to obtain a representation of R features for classification on CIFAR-10. All layers except the final (softmax) layer are frozen and are treated as a fixed feature-map. We then train the final layer of the network for the downstream task which yields a linear classifier on pretrained features. In Fig. 5, we plot the error of the whole meta-learning algorithm. d = 100, n2 = 40, T = 200, ΣT = (I20, 0.05 I80), ΣF = I100. |