Supervised learning: no loss no cry

Authors: Richard Nock, Aditya Menon

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments indicate that the BREGMANTRON outperforms the SLISOTRON, and that the loss it learns can be minimized by other algorithms for different tasks, thereby opening the interesting problem of loss transfer between domains.
Researcher Affiliation Collaboration Richard Nock 1 2 Aditya Krishna Menon 3 1Data61 (Australia) 2The Australian National University (Australia) 3Google Research (USA).
Pseudocode Yes Algorithm 0 SLISOTRON [...] Algorithm 1 BREGMANTRON
Open Source Code No The paper does not provide any explicit statement or link indicating the availability of open-source code for the described methodology.
Open Datasets Yes We compare performance on two standard benchmark datasets, the MNIST digits (mnist) and the fashion MNIST (fmnist)
Dataset Splits No The paper mentions using train and test sets but does not explicitly describe a validation set or its specific split percentage/quantity.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes In all experiments, we fix the following parameters for BREGMANTRON: we use a constant learning rate of η = 1 to perform the gradient update in Step 1, For Step 3, we fix nt = 10 2 and Nt = 1 for all iterations.