Adaptive Gradient-Based Meta-Learning Methods

Authors: Mikhail Khodak, Maria-Florina F. Balcan, Ameet S. Talwalkar

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 6 Empirical Results: Adaptive Methods for Few-Shot & Federated Learning
Researcher Affiliation Collaboration Mikhail Khodak Carnegie Mellon University khodak@cmu.edu Maria-Florina Balcan Carnegie Mellon University ninamf@cs.cmu.edu Ameet Talwalkar Carnegie Mellon University & Determined AI talwalkar@cmu.edu
Pseudocode Yes Algorithm 1: Generic online algorithm for gradient-based parameter-transfer meta-learning. and Algorithm 2: ARUBA: an approach for modifying a generic batch GBML method to learn a per-coordinate learning rate.
Open Source Code No The paper does not provide any explicit statement about releasing code or a link to a code repository for the methodology described.
Open Datasets Yes 20-way Omniglot [37] 5-way Mini-Image Net [46] and Shakespeare dataset [12]. These are standard, publicly available datasets with proper citations.
Dataset Splits No The paper mentions using standard benchmarks like Omniglot and Mini-Image Net, but it does not explicitly specify train/validation/test split percentages, sample counts, or refer to a specific publication detailing the splits for these experiments.
Hardware Specification No The paper does not specify any particular CPU or GPU models, or other hardware components used for running the experiments.
Software Dependencies No The paper mentions algorithms like Adam [36] and Fed Avg [41] but does not list any specific software dependencies or libraries with version numbers (e.g., Python, PyTorch, TensorFlow, CUDA versions) required for reproduction.
Experiment Setup Yes Algorithm 2: ARUBA: an approach for modifying a generic batch GBML method to learn a per-coordinate learning rate. Input: T tasks, update method for meta-initialization, within-task descent method, settings ε, ζ, p > 0 Initialize b1 ε21d, g1 ζ21d