Anirban Samaddar — accepted AI-conference papers

2024

REMEDI: Corrective Transformations for Improved Neural Entropy Estimation

Viktor Nilsson, Anirban Samaddar, Sandeep Madireddy, Pierre Nyquist

ICML 2024poster

Information theoretic quantities play a central role in machine learning. The recent surge in the complexity of data and models has increased the demand for accurate estimation of these quantities. However, as the dimension grows the estimation presents significant challenges, with existing methods…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2023

Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck

Anirban Samaddar, Sandeep Madireddy, Prasanna Balaprakash, Taps Maiti, Gustavo de los Campos, Ian Fischer

AISTATS 2023poster

The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a prior distribution that fixes the dimensionality across all the…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗