EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

Authors: Ondrej Bohdal, Yongxin Yang, Timothy Hospedales

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate Evo Grad on three substantial recent meta-learning applications, namely cross-domain few-shot learning with featurewise transformations, noisy label learning with Meta-Weight-Net and low-resource cross-lingual learning with meta representation transformation. The results show that Evo Grad significantly improves efficiency and enables scaling meta-learning to bigger architectures such as from Res Net10 to Res Net34.
Researcher Affiliation Collaboration Ondrej Bohdal1, Yongxin Yang1, Timothy Hospedales1,2 1 School of Informatics, The University of Edinburgh 2 Samsung AI Research Centre, Cambridge {ondrej.bohdal, yongxin.yang, t.hospedales}@ed.ac.uk
Pseudocode No The paper mentions an "Algorithm flow" but does not include a structured pseudocode or algorithm block.
Open Source Code Yes We provide source code for Evo Grad at https://github.com/ondrejbohdal/evograd.
Open Datasets Yes In this task we work with MNIST images [12] / (3.a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] Code and the instructions are a part of the supplemental material.
Dataset Splits Yes In this task we work with MNIST images [12], and assume that the validation and test sets are rotated by 30 compared to the conventionally oriented training images. / (3.b) Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] A short summary is provided in the main paper with further details in the supplemental material.
Hardware Specification Yes All our experiments are conducted on Titan X GPUs with 12GB of memory using K = 2 for Evo Grad.
Software Dependencies No The paper does not explicitly mention specific software dependencies with version numbers in the main text.
Experiment Setup Yes Further details and experimental settings are described in the supplementary material. / We use Evo Grad with 2 model copies, temperature τ = 0.05 and σ = 0.001 for ϵ σsign(N(0, I)). Our Le Net [13] base model is trained for 5 epochs. / Our second analysis studies the trajectories that parameters x, λ follow if they are both optimized online using SGD with learning rate of 0.1 for 5 steps, starting from five different positions (circles).