Pith. sign in

REVIEW 1 cited by

Backpropagation of Unrolled Solvers with Folded Optimization

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 2301.12047 v2 pith:DBTPUYZG submitted 2023-01-28 cs.LG cs.AI

classification cs.LGcs.AI
keywords optimizationanalyticalbackpropagationdifferentiationunrollingformissueslearning
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solution of an optimization problem, which typically lacks a closed form. One typical strategy is algorithm unrolling, which relies on automatic differentiation through the operations of an iterative solver. While flexible and general, unrolling can encounter accuracy and efficiency issues in practice. These issues can be avoided by analytical differentiation of the optimization, but current frameworks impose rigid requirements on the optimization problem's form. This paper provides theoretical insights into the backward pass of unrolled optimization, leading to a system for generating efficiently solvable analytical models of backpropagation. Additionally, it proposes a unifying view of unrolling and analytical differentiation through optimization mappings. Experiments over various model-based learning tasks demonstrate the advantages of the approach both computationally and in terms of enhanced expressiveness.

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. Structured Differentiable Optimization for Efficient Decision-focused Learning in Power Systems

    eess.SY 2026-08 conditional novelty 7.0 of 10

    DiffAPQP accelerates end-to-end decision-focused learning on IEEE 118-bus power systems by 2.27x to 6.39x over CvxpyLayers while keeping decision costs within 0.2%.

Pith tools