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(9)

• CASE: A Context-Aware Storage placement and retrieval Ecosystem

  AuthorGanesh Chandrasekaran, Boopathi Ramasamy, Pranay Dhondi, Pankaj Bhimrao Thorat, Rajesh Challa

  PublishedIEEE Access

  Date2021-12-21

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

  AuthorJungmin Kwon, Jeongseop Kim, Hyunseo Park, In Kwon Choi

  PublishedInternational Conference on Machine Learning (ICML)

  Date2021-07-22

• Personalizing Speech Start Point and End Point Detection in ASR Systems from Speaker Embeddings

  AuthorAditya Jayasimha, Periyasamy Paramasivam

  PublishedIEEE Spoken Language Technology Workshop (SLT)

  Date2021-01-19

View More

News(1)

• [Blog] 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).

Others(0)