7 papers
DIVERSED: Relaxed Speculative Decoding via Dynamic Ensemble Verification
Ziyi Wang, Siva Rajesh Kasa, Ankith M S +6
Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottleneck…
The Hidden Cost of Modeling P(X): Vulnerability to Membership Inference Attacks in Generative Text Classifiers
Owais Makroo, Siva Rajesh Kasa, Sumegh Roychowdhury +4
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despit…
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
Siva Rajesh Kasa, Karan Gupta, Sumegh Roychowdhury +7
The comparison between discriminative and generative classifiers has intrigued researchers since Efron's seminal analysis of logistic regression versus discriminant analysis. While…
Improved Inference of Gaussian Mixture Copula Model for Clustering and Reproducibility Analysis using Automatic Differentiation
Siva Rajesh Kasa, Vaibhav Rajan
Copulas provide a modular parameterization of multivariate distributions that decouples the modeling of marginals from the dependencies between them. Gaussian Mixture Copula Model…
Model-based Clustering using Automatic Differentiation: Confronting Misspecification and High-Dimensional Data
Siva Rajesh Kasa, Vaibhav Rajan
We study two practically important cases of model based clustering using Gaussian Mixture Models: (1) when there is misspecification and (2) on high dimensional data, in the light…
Automatic Differentiation in Mixture Models
Siva Rajesh Kasa, Vaibhav Rajan
In this article, we discuss two specific classes of models - Gaussian Mixture Copula models and Mixture of Factor Analyzers - and the advantages of doing inference with gradient de…