paper-with-me

홈 › Papers

SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients

2026-03-09 · Anselm Paulus, A. René Geist, Vít Musil, Sebastian Hoffmann, Onur Beker, Georg Martius arxiv

Automatic differentiation (AD) frameworks such as JAX and PyTorch have enabled gradient-based optimization for a wide range of scientific fields. Yet, many "hard" primitives in these libraries such as thresholding, Boolean logic, discrete indexing, and sorting operations yield zero or undefined gradients that are not useful for optimization. While numerous "soft" relaxations have been proposed that provide informative gradients, the respective implementations are fragmented across projects, making them difficult to combine and compare. This work introduces SoftJAX and SoftTorch, open-source, feature-complete libraries for soft differentiable programming. These libraries provide a variety of soft functions as drop-in replacements for their hard JAX and PyTorch counterparts. This includes (i) elementwise operators such as clip or abs, (ii) utility methods for manipulating Booleans and indices via fuzzy logic, (iii) axiswise operators such as sort or rank -- based on optimal transport or permutahedron projections, and (iv) offer full support for straight-through gradient estimation. Overall, SoftJAX and SoftTorch make the toolbox of soft relaxations easily accessible to differentiable programming, as demonstrated through benchmarking and a practical case study. Code is available at github.com/a-paulus/softjax and github.com/a-paulus/softtorch.

📄 PDF Abstract BibTeX arXiv:2603.08824

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Automatic differentiation is no panacea for phylogenetic gradient computation

2022-11-03 · Mathieu Fourment, Christiaan J. Swanepoel, Jared G. Galloway, Xiang Ji 외

Gradients of probabilistic model likelihoods with respect to their parameters are essential for modern computational statistics and machine learning. These calculations are readily available for arbitrary models via auto…

Variational Inference

fairret: a Framework for Differentiable Fairness Regularization Terms

2023-10-26 · Maarten Buyl, MaryBeth Defrance, Tijl De Bie

Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in…

Fairness

Automatic Differentiation for Adjoint Stencil Loops

2019-07-05 · Jan Hückelheim, Navjot Kukreja, Sri Hari Krishna Narayanan, Fabio Luporini 외

Stencil loops are a common motif in computations including convolutional neural networks, structured-mesh solvers for partial differential equations, and image processing. Stencil loops are easy to parallelise, and their…

Seismic Imaging

Automatic differentiation of Sylvester, Lyapunov, and algebraic Riccati equations

2020-11-23 · Ta-Chu Kao, Guillaume Hennequin

Sylvester, Lyapunov, and algebraic Riccati equations are the bread and butter of control theorists. They are used to compute infinite-horizon Gramians, solve optimal control problems in continuous or discrete time, and d…

TreeFlow: probabilistic programming and automatic differentiation for phylogenetics

2022-11-09 · Christiaan Swanepoel, Mathieu Fourment, Xiang Ji, Hassan Nasif 외

Probabilistic programming frameworks are powerful tools for statistical modelling and inference. They are not immediately generalisable to phylogenetic problems due to the particular computational properties of the phylo…

Probabilistic Programming