Scott Pesme

7 papers · 2020–2024 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (4)

Venues

NeurIPS (5) AISTATS (1) ICML (1)

Top co-authors

Nicolas Flammarion (7) Radu-Alexandru Dragomir (1) Mathieu Even (1) Loucas Pillaud-Vivien (1) Suriya Gunasekar (1) Hristo Papazov (1) Aymeric Dieuleveut (1)

Research topics

Machine Learning (7) Optimization & Theory · Machine Learning (7) Mathematics & Optimization (5) Optimization (5) Core Methods (4) Deep Learning (2) Optimization & Theory · Deep Learning (2)

Keywords

stochastic gradient descent (5) diagonal linear network (4) gradient flow (3) implicit regularization (2) implicit bia (2) mirror descent (1) sparse solution (1) linear network (1) saddle point (1) momentum gradient descent (1) continuous-time analysis (1) overparameterized regression (1) adversarial noise (1) convergence diagnostic (1) edge of stability (1) maximum margin classifier (1) stochastic gradient flow (1) generalization properties (1) implicit regularisation (1) step size scheduling (1)

Papers

Implicit Bias of Mirror Flow on Separable Data NeurIPS 2024 Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks AISTATS 2024 Saddle-to-Saddle Dynamics in Diagonal Linear Networks NeurIPS 2023 (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NeurIPS 2023 Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity NeurIPS 2021 On Convergence-Diagnostic based Step Sizes for Stochastic Gradient Descent ICML 2020 Online Robust Regression via SGD on the l1 loss NeurIPS 2020