Pith. sign in

REVIEW 3 cited by

PARQ: Piecewise-Affine Regularized Quantization

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 2503.15748 v1 pith:Z7LJINGG submitted 2025-03-19 cs.LG math.OC

classification cs.LGmath.OC
keywords parqmethodpiecewise-affineaggregateapproachaproxasymptoticcluster
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We develop a principled method for quantization-aware training (QAT) of large-scale machine learning models. Specifically, we show that convex, piecewise-affine regularization (PAR) can effectively induce the model parameters to cluster towards discrete values. We minimize PAR-regularized loss functions using an aggregate proximal stochastic gradient method (AProx) and prove that it has last-iterate convergence. Our approach provides an interpretation of the straight-through estimator (STE), a widely used heuristic for QAT, as the asymptotic form of PARQ. We conduct experiments to demonstrate that PARQ obtains competitive performance on convolution- and transformer-based vision tasks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Beyond Discreteness: Sample Complexity Analysis of Straight-Through Estimator for 1-bit Quantization

    cs.LG 2025-05 conditional novelty 7.0 of 10

    For a two-layer binary network with Gaussian inputs, O(n^2) samples guarantee ergodic convergence of STE training and O(n^4) guarantee that iterates revisit the optimal weights, even under label noise.

  2. CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

    cs.LG 2025-10 conditional novelty 6.0 of 10

    CAGE, a curvature-aware correction that adds the quantization error to the gradient, reduces loss in low-bit quantization-aware training, letting 3-bit CAGE-trained models match 4-bit baseline-trained models.

  3. TorchAO: PyTorch-Native Training-to-Serving Model Optimization

    cs.LG 2025-07 conditional novelty 5.0 of 10

    TorchAO delivers a PyTorch-native, end-to-end workflow for FP8 training, QAT, PTQ, and sparsity, with benchmarked speedups and production use in quantized Llama releases.

Pith tools