Rosca, Mihaela

8 publications

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

NeurIPSW 2020 A Case for New Neural Networks Smoothness Constraints Mihaela Rosca, Theophane Weber, Arthur Gretton, Shakir Mohamed

JMLR 2020 Monte Carlo Gradient Estimation in Machine Learning Shakir Mohamed, Mihaela Rosca, Michael Figurnov, Andriy Mnih

ICML 2019 Deep Compressed Sensing Yan Wu, Mihaela Rosca, Timothy Lillicrap

NeurIPS 2019 Training Language GANs from Scratch Cyprien de Masson d'Autume, Shakir Mohamed, Mihaela Rosca, Jack Rae

ICML 2018 Learning Implicit Generative Models with the Method of Learned Moments Suman Ravuri, Shakir Mohamed, Mihaela Rosca, Oriol Vinyals

ICLR 2018 Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence at Every Step William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow