Pith. sign in

REVIEW 7 cited by

Equinox: neural networks in JAX via callable PyTrees and filtered transformations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2111.00254 v1 pith:6HLLENLN submitted 2021-10-30 cs.LG cs.PL

classification cs.LGcs.PL
keywords equinoxfunctionfunctionsparameterisedfunctionalneuralpytreestransformations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

JAX and PyTorch are two popular Python autodifferentiation frameworks. JAX is based around pure functions and functional programming. PyTorch has popularised the use of an object-oriented (OO) class-based syntax for defining parameterised functions, such as neural networks. That this seems like a fundamental difference means current libraries for building parameterised functions in JAX have either rejected the OO approach entirely (Stax) or have introduced OO-to-functional transformations, multiple new abstractions, and been limited in the extent to which they integrate with JAX (Flax, Haiku, Objax). Either way this OO/functional difference has been a source of tension. Here, we introduce `Equinox', a small neural network library showing how a PyTorch-like class-based approach may be admitted without sacrificing JAX-like functional programming. We provide two main ideas. One: parameterised functions are themselves represented as `PyTrees', which means that the parameterisation of a function is transparent to the JAX framework. Two: we filter a PyTree to isolate just those components that should be treated when transforming (`jit', `grad' or `vmap'-ing) a higher-order function of a parameterised function -- such as a loss function applied to a model. Overall Equinox resolves the above tension without introducing any new programmatic abstractions: only PyTrees and transformations, just as with regular JAX. Equinox is available at \url{https://github.com/patrick-kidger/equinox}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Fortran General-Purpose Transpiler: Proof of Concept

    cs.PL 2026-07 conditional novelty 7.0 of 10

    FGPT deterministically translates isolated Fortran procedures into numerically verified NumPy and JAX/Equinox modules, with forward outputs matching Fortran to ~1e-9, but explicit auto-differentiation is not yet implemented.

  2. Neural Network-Augmented Pfaffian Wave-functions for Scalable Simulations of Interacting Fermions

    cond-mat.str-el 2025-07 conditional novelty 7.0 of 10

    A neural-network Pfaffian wavefunction with hidden fermions achieves state-of-the-art variational accuracy on the 2D Hubbard model and scales via low-rank updates and sublattice symmetry.

  3. Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures

    cs.CL 2025-06 conditional novelty 7.0 of 10

    A two-level mixture-of-experts sparse autoencoder models parent and child concepts together, improving reconstruction and reducing feature redundancy on Gemma 2-2B activations compared to flat top-k SAEs.

  4. Fast, accurate, and differentiable: a neural-network surrogate for NRSur7dq4 precessing binary black hole waveforms

    gr-qc 2026-07 accept novelty 6.0 of 10

    A piecewise MLP surrogate emulates NRSur7dq4 over its full domain at NR-faithful accuracy with ~1 ms GPU latency and a fully differentiable JAX likelihood pipeline.

  5. Differentiable Cardiac Electrophysiology Simulations for Dynamical State and Parameter Estimation

    physics.med-ph 2026-07 conditional novelty 6.0 of 10

    A differentiable solver for cardiac reaction-diffusion waves recovers hidden states and parameters of the Aliev-Panfilov model from sparse, surface-only, or noisy voltage observations, including two experimental monol...

  6. Biomechanics-aware Multi-view Markerless Motion Capture of Dexterous Hand Movements

    cs.CV 2026-07 conditional novelty 5.0 of 10

    End-to-end biomechanics-aware optimization recovers plausible multi-joint hand kinematics from multi-view markerless video more robustly than two-stage triangulation-plus-IK, especially under object occlusion.

  7. Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation

    stat.ML 2026-05 conditional novelty 4.0 of 10

    A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.

Pith tools