Timezone: »

 
Contributed Talks in Session 1 (Zoom)
Sebastian Stich · Futong Liu · Abdurakhmon Sadiev · Frederik Benzing · Simon Roburin

Mon Dec 13 05:00 AM -- 05:30 AM (PST) @

Oral (10 min)

  • Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation, Futong Liu

Spotlights (5 min)

  • Decentralized Personalized Federated Learning: Lower Bounds and Optimal Algorithm for All Personalization Modes, Abdurakhmon Sadiev

  • Fast, Exact Subsampled Natural Gradients and First-Order KFAC, Frederik Benzing

  • Spherical Perspective on Learning with Normalization Layers, Simon Roburin

There will be a Q&A in the last 5 minutes for all speakers. Abstracts for the talks are below the schedule.

Author Information

Sebastian Stich (CISPA)

Dr. [Sebastian U. Stich](https://sstich.ch/) is a faculty at the CISPA Helmholtz Center for Information Security. Research interests: - *methods for machine learning and statistics*—at the interface of theory and practice - *collaborative learning* (distributed, federated and decentralized methods) - *optimization for machine learning* (adaptive stochastic methods and generalization performance)

Futong Liu (EPFL)
Abdurakhmon Sadiev (Moscow Institute of Physics and Technology)
Frederik Benzing (ETH Zurich)
Simon Roburin (ENPC; valeo.ai)

More from the Same Authors