Pith. sign in

REVIEW 4 cited by

A survey and taxonomy of loss functions in machine 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 2301.05579 v2 pith:CCEOB5LX submitted 2023-01-13 cs.LG

Lorenzo Ciampiconi , Adam Elwood , Marco Leonardi , Ashraf Mohamed , Alessandro Rozza This is my paper · ORCID
classification cs.LG
keywords functionslosssurveylearningmachinemodelingtaxonomyacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Most state-of-the-art machine learning techniques revolve around the optimisation of loss functions. Defining appropriate loss functions is therefore critical to successfully solving problems in this field. In this survey, we present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling. We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts. This survey is intended as a resource for undergraduate, graduate, and Ph.D. students, as well as researchers seeking a deeper understanding of loss functions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. A Unified Framework for In-Context Learning with Causal and Masked Language Models

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Masked and causal pretraining yield same-order k-shot excess-risk bounds under Wasserstein regularity, and a Masked Pair Encoder matches GPT-2-style ICL on synthetic function classes.

  2. Reconstruction of Primordial Power Spectrum from Gravitational Waves of High-Redshift Black Hole Binaries

    astro-ph.CO 2026-07 conditional novelty 6.0 of 10

    Gradient-descent inversion of redshifted BBH mass distributions recovers the PBH mass function and, via regularized Press-Schechter, a candidate O(10^{-2}) bump in the small-scale primordial power spectrum.

  3. Neuro-Argumentative Learning with Case-Based Reasoning

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Gradual AA-CBR learns a case-based argumentation debate end-to-end and matches a single-layer neural network on four datasets while supporting multi-class and continuous features.

  4. Bulk-boundary decomposition of neural networks

    cs.LG 2025-11 reject novelty 3.0 of 10

    The paper reframes SGD training of deep networks as a local Lagrangian with data confined to the boundaries, but the advertised energy continuity equation is absent from the body.

Pith tools