LR

Lisheng Ren

cs.LGcs.DSstat.MLcs.CCmath.STstat.TH

On Valency

published · living versions

W_xa66wg4f·v1 · currentpublished

Beyond Multi-Index Models: Learning Intersections of Degree-2 PTFs

with Ilias Diakonikolas, Daniel M. Kane, Mingchen Ma, Trung Tran

1 version

Preprints & journals

9 papers in the corpus · 2022–2025

Learning Intersections of Two Margin Halfspaces under Factorizable Distributions2511.09832v2 · Ilias Diakonikolas, Mingchen Ma, Lisheng Ren et al.2025 · 0 citationsarXiv

Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-index Models2505.21475v1 · Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane et al.2025 · 0 citationsarXiv

Faster Algorithms for Agnostically Learning Disjunctions and their Implications2504.15244v1 · Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren2025 · 0 citationsarXiv

Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise2502.11413v1 · Ilias Diakonikolas, Mingchen Ma, Lisheng Ren et al.2025 · 0 citationsarXiv

Reliable Learning of Halfspaces under Gaussian Marginals2411.11238v1 · Ilias Diakonikolas, Lisheng Ren, Nikos Zarifis2024 · 0 citationsarXiv

SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions2403.04744v1 · Ilias Diakonikolas, Daniel Kane, Lisheng Ren et al.2024 · 2 citationsarXiv

Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals2302.06512v1 · Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren2023 · 3 citationsarXiv

SQ Lower Bounds for Learning Single Neurons with Massart Noise2210.09949v1 · Ilias Diakonikolas, Daniel M. Kane, Lisheng Ren et al.2022 · 0 citationsarXiv

Cryptographic Hardness of Learning Halfspaces with Massart Noise2207.14266v1 · Ilias Diakonikolas, Daniel M. Kane, Pasin Manurangsi et al.2022 · 6 citationsarXiv

Career total: 14 works. 9 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.