Profiles2022-2026
Arthur Jacot
Courant Institute, NYU
9Papers
4Last author
8Unique co-authors
5First author
2Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle EscapeAuthor 3 of 3ICLR 2026 · 4 citations
- How DNNs break the Curse of Dimensionality: Compositionality and Symmetry LearningAuthor 1 of 3ICLR 2025
- Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural CollapseAuthor 1 of 4ICLR 2025
- Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rankAuthor 2 of 2ICLR 2024 · 27 citations
- Mixed Dynamics In Linear Networks: Unifying the Lazy and Active RegimesAuthor 3 of 3NeurIPS 2024 · 18 citations
- Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature LearningAuthor 2 of 2ICML 2024 · 9 citations
- Bottleneck Structure in Learned Features: Low-Dimension vs Regularity TradeoffAuthor 1 of 1NeurIPS 2023 · 20 citations
- Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear FunctionsAuthor 1 of 1ICLR 2023 · 2 citations
- Feature Learning in -regularized DNNs: Attraction/Repulsion and SparsityAuthor 1 of 4NeurIPS 2022 · 22 citations
