A Free-Energy Principle for Representation Learning

Authors: Yansong Gao, Pratik Chaudhari

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental validation of the theoretical results is provided on standard imageclassification datasets.
Researcher Affiliation Academia 1University of Pennsylvania, USA. Correspondence to: Yansong Gao <gaoyans@sas.upenn.edu>, Pratik Chaudhari <pratikac@seas.upenn.edu>.
Pseudocode No The paper describes algorithms and processes textually and through equations, but does not include any clearly labeled pseudocode or algorithm blocks.
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 use the MNIST (Le Cun et al., 1998) and CIFAR-10 (Krizhevsky, 2009) datasets for our experiments.
Dataset Splits No The paper mentions 'validation loss' and 'validation accuracy' in figures and text (e.g., Figures 2 and 3), implying the use of a validation set, but it does not specify the dataset splits (e.g., percentages or exact counts for train/validation/test) in the main text.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, or cloud resources) used for running the experiments.
Software Dependencies No The paper mentions optimizers like Adam, but it does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes Given a value of the Lagrange multipliers (λ, γ) we first find a model on the equilibrium surface by training from scratch for 120 epochs with the Adam optimizer (Kingma & Ba, 2014); the learning rate is set to 10 3 and drops by a factor of 10 every 50 epochs. The maximum value of the learning rate is set to 1.5 10 3. We train on source dataset for 300 epochs with Adam and a learning rate of 1E-3 that drops by a factor of 10 after every 120 epochs.