Pith. sign in

REVIEW 1 cited by

Towards Learning High-Precision Least Squares Algorithms with Sequence Models

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 2503.12295 v1 pith:DM55SWHH submitted 2025-03-15 cs.LG cs.NAmath.NA

classification cs.LGcs.NAmath.NA
keywords algorithmsnumericalgradienthigh-precisionleastsquaresarchitecturesdescent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical analysis: (1) machine precision, i.e. we want to obtain solutions that are accurate to near floating point error, and (2) numerical generality, i.e. we want them to apply broadly across problem instances. We find that prior approaches using Transformers fail to meet these criteria, and identify limitations present in existing architectures and training procedures. First, we show that softmax Transformers struggle to perform high-precision multiplications, which prevents them from precisely learning numerical algorithms. Second, we identify an alternate class of architectures, comprised entirely of polynomials, that can efficiently represent high-precision gradient descent iterates. Finally, we investigate precision bottlenecks during training and address them via a high-precision training recipe that reduces stochastic gradient noise. Our recipe enables us to train two polynomial architectures, gated convolutions and linear attention, to perform gradient descent iterates on least squares problems. For the first time, we demonstrate the ability to train to near machine precision. Applied iteratively, our models obtain 100,000x lower MSE than standard Transformers trained end-to-end and they incur a 10,000x smaller generalization gap on out-of-distribution problems. We make progress towards end-to-end learning of numerical algorithms for least squares.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. BWLer: Barycentric Weight Layer Elucidates a Precision-Conditioning Tradeoff for PINNs

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adding a barycentric interpolation layer to PINNs lifts their precision ceiling, achieving up to 1e-13 relative error on smooth PDEs, while exposing a tradeoff between accuracy and loss conditioning.

Pith tools