Implicit Regularization for Optimal Sparse Recovery

Tomas Vaskevicius, Varun Kanade, Patrick Rebeschini

Feb-12-2026, 07:46:22 GMT–Neural Information Processing Systems

Ifwecanset1 /w max η 1 / (20 w max) thentheiterationcomplexityof Theorem 1 reduces to O ( κeff( w ) logα 1). Themagnitudeofw max is, however, anunknownquantity.

artificial intelligence, machine learning, theorem 1, (12 more...)

Neural Information Processing Systems

Feb-12-2026, 07:46:22 GMT

Conferences PDF

Country:
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America
  - Canada > British Columbia
    - Metro Vancouver Regional District > Vancouver (0.04)
  - United States > New York (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning (0.97)

Duplicate Docs Excel Report

Title
Implicit Regularization for Optimal Sparse Recovery

Similar Docs Excel Report more

Title	Similarity	Source
None found