ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Arthur Jacot

Arthur Jacot

1

Affiliations

Affiliations

EPFL

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:32 PM AMS

8

papers

143

total citations

papers (8)

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

NEURIPS 2020arXiv

Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

NEURIPS 2023arXiv

Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning

DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel

NEURIPS 2021arXiv

Feature Learning in $L_2$-regularized DNNs: Attraction/Repulsion and Sparsity