https://github.com/atomicarchitects/priceoffreedom

[ICML'25] The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products

https://github.com/atomicarchitects/priceoffreedom

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.5%) to scientific vocabulary

Keywords

equivariance machine-learning symmetry tensor-product
Last synced: 9 months ago · JSON representation

Repository

[ICML'25] The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products

Basic Info
Statistics
  • Stars: 10
  • Watchers: 3
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
equivariance machine-learning symmetry tensor-product
Created about 2 years ago · Last pushed 12 months ago
Metadata Files
Readme

README.md

[ICML'25] Price of Freedom: Exploring Tradeoffs between Expressivity and Computational Efficiency in Equivariant Tensor Products

The official implementation of the Price of Freedom: Exploring Tradeoffs between Expressivity and Computational Efficiency in Equivariant Tensor Products, published at ICML 2025.

Installation

We recommend using uv:

bash uv sync source .venv/bin/activate uv pip install -e .

Alternatively, you can install the dependencies manually: bash python -m venv .venv source .venv/bin/activate uv pip install -r requirements.in

Tetris Experiments

bash bash shell/run_tetris_experiments.sh

3BPA experiments

Checkout experiments/Gaunt-Tensor-Product-S2Grid. Refer to the original code for reproducing the experiments

Plotting

experiments/Gaunt-Tensor-Product-S2Grid/analyze_results.ipynb

Benchmarking experiments

CPU

bash bash shell/run_cpu_timing.sh

GPU

bash bash shell/run_gpu_timing.sh

Nsight Compute installation needed. Make sure the GPU counters are enabled.

bash shell/run_nsight_profiling.sh

Plotting

notebooks/benchmarking_viz

Owner

  • Name: The Atomic Architects
  • Login: atomicarchitects
  • Kind: organization
  • Location: United States of America

Research Group of Prof. Tess Smidt

GitHub Events

Total
  • Issues event: 3
  • Watch event: 7
  • Issue comment event: 5
  • Push event: 15
  • Fork event: 1
  • Create event: 1
Last Year
  • Issues event: 3
  • Watch event: 7
  • Issue comment event: 5
  • Push event: 15
  • Fork event: 1
  • Create event: 1

Dependencies

requirements.txt pypi
  • absl-py *
  • e3nn_jax *
  • flax *
  • jax *
  • jraph *
  • ml_collections *
  • nvtx *
  • optax *
  • pandas *
  • pyg_lib *
  • rdkit *
  • torch *
  • torch-geometric *
  • torch_cluster *
  • torch_scatter *
  • torch_sparse *
  • torch_spline_conv *
  • wandb *