5 papers
Sparsity Saves Compute, Not Samples: Oracle Inequalities for Dense and Sparse Mixture of Experts
Sagar Ghosh, Huy Nguyen, Alessandro Rinaldo
Mixture-of-Experts (MoE) models combine specialized experts through an input-dependent routing mechanism, and their sparse variants underpin many modern large-scale systems. Yet th…
Convex Clustering Redefined: Robust Learning with the Median of Means Estimator
Sourav De, Koustav Chowdhury, Bibhabasu Mandal +4
Clustering approaches that utilize convex loss functions have recently attracted growing interest in the formation of compact data clusters. Although classical methods like k-means…
Transformers Are Universally Consistent
Sagar Ghosh, Kushal Bose, Swagatam Das
Despite their central role in the success of foundational models and large-scale language modeling, the theoretical foundations governing the operation of Transformers remain only…
On the Universal Statistical Consistency of Expansive Hyperbolic Deep Convolutional Neural Networks
Sagar Ghosh, Kushal Bose, Swagatam Das
The emergence of Deep Convolutional Neural Networks (DCNNs) has been a pervasive tool for accomplishing widespread applications in computer vision. Despite its potential capability…
Consistent Spectral Clustering in Hyperbolic Spaces
Sagar Ghosh, Swagatam Das
Clustering, as an unsupervised technique, plays a pivotal role in various data analysis applications. Among clustering algorithms, Spectral Clustering on Euclidean Spaces has been…