no code implementations • 24 Apr 2024 • Oriol Barbany, Michael Huang, Xinliang Zhu, Arnab Dhua
Multimodal search has become increasingly important in providing users with a natural and effective way to ex-press their search intentions.
no code implementations • 5 Feb 2024 • Michael Huang, Vishal Gupta
This is the first such result in misspecified settings and we provide numerical evidence confirming our PG losses substantively outperform existing proposals when the underlying model is misspecified and the noise is not centrally symmetric.
no code implementations • 21 Sep 2023 • Uday Kumar Reddy Vengalam, Andrew Hahn, Yongchao Liu, Anshujit Sharma, Hui Wu, Michael Huang
Due to 5G deployment, there is significant interest in LDPC decoding.
no code implementations • 1 May 2023 • Anshujit Sharma, Matthew Burns, Andrew Hahn, Michael Huang
With experimental analyses, we show that such an Augmented Ising Machine for SAT (AIMS), outperforms state-of-the-art software-based, GPU-based and conventional hardware SAT solvers by orders of magnitude.
no code implementations • 26 Jul 2021 • Vishal Gupta, Michael Huang, Paat Rusmevichientong
Motivated by the poor performance of cross-validation in settings where data are scarce, we propose a novel estimator of the out-of-sample performance of a policy in data-driven optimization. Our approach exploits the optimization problem's sensitivity analysis to estimate the gradient of the optimal objective value with respect to the amount of noise in the data and uses the estimated gradient to debias the policy's in-sample performance.