Blog(1)

• ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

  Recently we proposed a new optimization algorithm called Adaptive Sharpness-Aware Minimization (ASAM), which pushes the limit of deep learning via PAC-Bayesian theory. ASAM has been improving generalization performance for various tasks leveraging geometry of loss landscape, which is highly correlated with generalization. In recognition of its theoretical contribution and practicality, our paper was published at the 38th International Conference on Machine Learning (ICML 2021).

Research Areas(0)

Publications(25)

• TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge

  AuthorYoung D. Kwon, Rui Li, Stylianos I.Venieris

  PublishedInternational Conference on Machine Learning (ICML)

  Date2024-07-23

• An MVDR-Embedded U-Net Beamformer for Effective and Robust Multichannel Speech Enhancement

  AuthorChinghua Lee,Chouchang Yang,Yilin Shen,Hongxia Jin

  PublishedIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

  Date2024-04-14

• Deep Neural Network Models Trained with a Fixed Random Classifier Transfer Better Across Domains

  AuthorUmberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay

  PublishedInternational Conference on Acoustics, Speech and Signal Processing (ICASSP)

  Date2024-03-18

View More

News(2)

• [Blog] Smart at what cost? Characterising Mobile DNNs in the wild

  Smartphones are all around us, today, available in various tiers and form factors. A large part of what makes them ‘smart’ is (i) their integration of sensors, so as to ‘sense”’ their environment, and (ii) the ability to run ML models, so as to ‘understand’ their environment.

• [Blog] Zero-Cost Neural Architecture Search

  Neural architecture search (NAS) is quickly becoming the standard methodology for designing deep neural networks (DNNs).

Others(0)