Dherin, Benoit

11 publications

TMLR 2025 How Iteration Composition Influences Convergence and Stability in Deep Learning Benoit Dherin, Benny Avelin, Anders Karlsson, Hanna Mazzawi, Javier Gonzalvo, Michael Munn

ICML 2024 Deep Fusion: Efficient Network Training via Pre-Trained Initializations Hanna Mazzawi, Javier Gonzalvo, Michael Wunder, Sammy Jerome, Benoit Dherin

NeurIPS 2024 The Impact of Geometric Complexity on Neural Collapse in Transfer Learning Michael Munn, Benoit Dherin, Javier Gonzalvo

ICMLW 2023 A Margin-Based Multiclass Generalization Bound via Geometric Complexity Michael Munn, Benoit Dherin, Javier Gonzalvo

NeurIPSW 2023 Implicit Biases in Multitask and Continual Learningfrom a Backward Error Analysis Perspective Benoit Dherin

ICMLW 2023 Morse Neural Networks for Uncertainty Quantification Benoit Dherin, Huiyi Hu, Jie Ren, Michael W Dusenberry, Balaji Lakshminarayanan

TMLR 2023 On a Continuous Time Model of Gradient Descent Dynamics and Instability in Deep Learning Mihaela Rosca, Yan Wu, Chongli Qin, Benoit Dherin

NeurIPS 2022 Why Neural Networks Find Simple Solutions: The Many Regularizers of Geometric Complexity Benoit Dherin, Michael Munn, Mihaela Rosca, David Barrett

ICML 2021 Discretization Drift in Two-Player Games Mihaela C Rosca, Yan Wu, Benoit Dherin, David Barrett

ICLR 2021 Implicit Gradient Regularization David Barrett, Benoit Dherin

ICLR 2021 On the Origin of Implicit Regularization in Stochastic Gradient Descent Samuel L Smith, Benoit Dherin, David Barrett, Soham De