Optimization
Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs
Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system.
Amortized Eigendecomposition for Neural Networks
By uncovering the structure of networks, eigendecomposition allows us to enforce low-rankness, ensuring generalization, robustness, and computational efficiency.
VISA: Variational Inference with Sequential Sample-Average Approximations
We perform experiments on high-dimensional Gaussians, Lotka-V olterra dynamics, and a Pickover attractor.
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint Chi-Chang Lee
As such, we prevent policies from merely exploiting heuristic rewards without improving the task reward.
Partial Transportability for Domain Generalization
Our results are corroborated with experiments.
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
In this paper, we introduce a novel robust attention mechanism designed to enhance the resilience of transformer-based architectures.
