Strong Lottery Ticket Hypothesis with ϵ–Perturbation + Sufficient conditions for non-asymptotic convergence of Riemannian optimization methods + How Does Sharpness-Aware Minimization Minimizes Sharpness?
Dec 2, 2022
Speakers
Fangshuo Liao
Speaker · 0 followers
Vishwak Srinivasan
Speaker · 0 followers
Zhiyuan Li
Speaker · 0 followers
About
Three (15 min) contributed talks in this session. * **Fangshuo Liao**, *Strong Lottery Ticket Hypothesis with ϵ–Perturbation* * **Vishwak Srinivasan**, *Sufficient conditions for non-asymptotic convergence of Riemannian optimization methods* * **Zhiyuan Li**, *How Does Sharpness-Aware Minimization Minimizes Sharpness?*Three (15 min) contributed talks in this session. * **Fangshuo Liao**, *Strong Lottery Ticket Hypothesis with ϵ–Perturbation* * **Vishwak Srinivasan**, *Sufficient conditions for non-asymptotic convergence of Riemannian optimization methods* * **Zhiyuan Li**, *How Does Sharpness-Aware Minimization Minimizes Sharpness?*…
Organizer
NeurIPS 2022
Account · 962 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
IALE: Imitating Active Learner Ensembles
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Understanding stock market instability via graph auto-encoders
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Compression supports low-dimensional representations of behavior across neural circuits
Watch later
Dale Zhou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Best Combination for Efficient N:M Sparsity
Watch later
Yuxin Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
Watch later
Bodhisattwa Prasad Majumder, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%