Skip to content
conftrace_

Arthur Jacot

15 papers · 2018–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (18) πŸƒ Academic Marathon Β· Sprint 🌍 Conference Polyglot Β· Bronze πŸŒ‰ Interdisciplinary Bridge Β· Bronze 🐣 Hot Topic Early Bird
πŸ† Keyword Champion πŸ‘‘ Triple Crown 🧭 Keyword Pioneer πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner πŸ—ƒοΈ Keyword Collector (67) πŸ’Ž Century Club Β· Bronze

Venues

ICLR (6) NeurIPS (6) ICML (3)

Top co-authors

Clement Hongler (6) Franck Gabriel (5) Berfin Simsek (3) Francesco Spadaro (3) Yuxiao Wen (2) Zihan Wang (2) Santiago Aranguri (1) Nicholas Matthew Boffi (1) Ingvar Ziemann (1) Seok Hoan Choi (1)

Research topics

Machine Learning (14) Optimization & Theory Β· Machine Learning (13) Deep Learning (9) Optimization & Theory Β· Deep Learning (6) Core Methods (5) Architectures (4) Mathematics & Optimization (2) Computer Vision (1) Analysis (1) Learning Types (1) Mathematics (1) Optimization (1)

Keywords

learning theory (3) deep neural network (3) neural network (3) neural tangent kernel (3) feature learning (2) gradient descent (2) implicit bia (2) kernel ridge regression (2) kernel methods (2) curse of dimensionality (1) matrix completion (1) generalization error (1) sample complexity (1) l2 regularization (1) gaussian process (1) stochastic gradient descent (1) random matrix theory (1) distribution learning (1) generalization bound (1) loss landscape (1)

Papers

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning ICLR 2025 Shallow diffusion networks provably learn hidden low-dimensional structure ICLR 2025 Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse ICLR 2025 Implicit bias of SGD in L_2-regularized linear DNNs: One-way jumps from high to low rank ICLR 2024 Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes NeurIPS 2024 Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning ICML 2024 Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff NeurIPS 2023 Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions ICLR 2023 Feature Learning in L_2-regularized DNNs: Attraction/Repulsion and Sparsity NeurIPS 2022 DNN-based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel NeurIPS 2021 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021 Implicit Regularization of Random Feature Models ICML 2020 Kernel Alignment Risk Estimator: Risk Prediction from Training Data NeurIPS 2020 The asymptotic spectrum of the Hessian of DNN throughout training ICLR 2020 Neural Tangent Kernel: Convergence and Generalization in Neural Networks NeurIPS 2018