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).

Focus Areas(0)

Research Achievements(18)

• IMPROVING HEART RATE AND HEART RATE VARIABILITY ESTIMATION FROM VIDEO THROUGH A HR-RR-TUNED FILTER

  AuthorRetiree,Li Zhu,Korosh Vatanparvar,Jilong Kuang,Alex Gao

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

  Date2023-06-04

• FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout

  AuthorStefanos

  PublishedNeural Information Processing Systems (NeurIPS)

  Date2021-11-07

• Learning Multi-Scale Photo Exposure Correction

  AuthorMahmoud Afifi, Konstantinos G. Derpanis, Björn Ommer, Michael S. Brown

  PublishedComputer Vision and Pattern Recognition (CVPR)

  Date2021-06-19

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)