no code implementations • 12 Apr 2024 • Etash Guha, Shlok Natarajan, Thomas Möllenhoff, Mohammad Emtiyaz Khan, Eugene Ndiaye
Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed.
1 code implementation • 11 Mar 2024 • Etash Guha, Vihan Lakshman
While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence.
no code implementations • 17 Oct 2022 • Guanghui Wang, Rafael Hanashiro, Etash Guha, Jacob Abernethy
The classical Perceptron algorithm of Rosenblatt can be used to find a linear threshold function to correctly classify $n$ linearly separable data points, assuming the classes are separated by some margin $\gamma > 0$.