Statistical Learning
A New Family of Generalization Bounds Using Samplewise Evaluated CMI
We demonstrate the generality of this framework by recovering and extending previously known information-theoretic bounds.
40e56dabe12095a5fc44a6e4c3835948-Supplemental-Conference.pdf
This work was fully funded by NVIDIA.
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
Recent findings demonstrate that modern neural networks trained by full-batch gradient descent typically enter a regime called Edge of Stability (EOS).
Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting
Transformers have shown great power in time series forecasting due to their global-range modeling ability.
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques Bokun Wang Texas A&M University, United States
Work done when the author was a research intern at KAUST, Saudi Arabia.