Pith. sign in

REVIEW 3 cited by

Generalized Inner Loop Meta-Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 1910.01727 v2 pith:SOLO2ZGH submitted 2019-10-03 cs.LG stat.ML

Edward Grefenstette , Brandon Amos , Denis Yarats , Phu Mon Htut , Artem Molchanov , Franziska Meier , Douwe Kiela , Kyunghyun Cho
show 1 more author
Soumith Chintala
This is my paper · ORCID
classification cs.LGstat.ML
keywords approachesmeta-learningalgorithmlearninglibrarypatternablationanalysis
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Many (but not all) approaches self-qualifying as "meta-learning" in deep learning and reinforcement learning fit a common pattern of approximating the solution to a nested optimization problem. In this paper, we give a formalization of this shared pattern, which we call GIMLI, prove its general requirements, and derive a general-purpose algorithm for implementing similar approaches. Based on this analysis and algorithm, we describe a library of our design, higher, which we share with the community to assist and enable future research into these kinds of meta-learning approaches. We end the paper by showcasing the practical applications of this framework and library through illustrative experiments and ablation studies which they facilitate.

Discussion (0). Continue with ORCID 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. Optimization under Persistent State-Dependent Bias: Gradient-based Method and Complexity Analysis

    math.OC 2026-07 reject novelty 6.0 of 10

    Residual Learning, a proposed bilevel gradient method, claims exact convergence under state-dependent analog-hardware bias with rate O~(kappa1*kappa2^4*sigma^2/(mu*K)).

  2. A Planning Framework for Adaptive Labeling

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A planning framework for adaptive labeling where a smoothed auto-differential policy gradient (Smoothed-Autodiff) selects batches to minimize final posterior uncertainty, outperforming active-learning heuristics and R...

  3. TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation

    cs.IR 2025-02 conditional novelty 6.0 of 10

    TD3 factorizes a synthetic sequence summary into user, time, item, and core factors via Tucker decomposition, and trains recommenders on this summary with a feature-alignment meta-objective.

Pith tools