3 citations · 10 across the 12 of their papers we have counts for
16 papers
Memorization in Fine-Tuned Large Language Models
Danil Savine
This study investigates the mechanisms and factors influencing memorization in fine-tuned large language models (LLMs), with a focus on the medical domain due to its privacy-sensit…
Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory
Lucas Gnecco-Heredia, Matteo Sammut, Muni Sreenivas Pydi +3
Randomization as a mean to improve the adversarial robustness of machine learning models has recently attracted significant attention. Unfortunately, much of the theoretical analys…
Optimal Classification under Performative Distribution Shift
Edwige Cyffers, Muni Sreenivas Pydi, Jamal Atif +1
Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public de…
Memorization in Attention-only Transformers
Léo Dana, Muni Sreenivas Pydi, Yann Chevaleyre
Recent research has explored the memorization capacity of multi-head attention, but these findings are constrained by unrealistic limitations on the context size. We present a nove…
Differentially Private Gradient Flow based on the Sliced Wasserstein Distance
Ilana Sebag, Muni Sreenivas Pydi, Jean-Yves Franceschi +4
Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling. This can be achieved through either differentially private stochas…
Optimal Budgeted Rejection Sampling for Generative Models
Alexandre Verine, Muni Sreenivas Pydi, Benjamin Negrevergne +1
Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models. However, these methods are only optimal under an unlimit…
Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows
Alexandre Verine, Benjamin Negrevergne, Muni Sreenivas Pydi +1
Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models. Current state-of-the-art models primaril…
Training Normalizing Flows with the Precision-Recall Divergence
Alexandre Verine, Benjamin Negrevergne, Muni Sreenivas Pydi +1
Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric. To address this, recent works p…
On the Role of Randomization in Adversarially Robust Classification
Lucas Gnecco-Heredia, Yann Chevaleyre, Benjamin Negrevergne +2
Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed…
Robust empirical risk minimization via Newton's method
Eirini Ioannou, Muni Sreenivas Pydi, Po-Ling Loh
A new variant of Newton's method for empirical risk minimization is studied, where at each iteration of the optimization algorithm, the gradient and Hessian of the objective functi…
The Many Faces of Adversarial Risk
Muni Sreenivas Pydi, Varun Jog
Adversarial risk quantifies the performance of classifiers on adversarially perturbed data. Numerous definitions of adversarial risk -- not all mathematically rigorous and differin…
Adversarial Risk via Optimal Transport and Optimal Couplings
Muni Sreenivas Pydi, Varun Jog
Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial class…
Active Learning with Importance Sampling
Muni Sreenivas Pydi, Vishnu Suresh Lokhande
We consider an active learning setting where the algorithm has access to a large pool of unlabeled data and a small pool of labeled data. In each iteration, the algorithm chooses f…
Graph-Based Ascent Algorithms for Function Maximization
Muni Sreenivas Pydi, Varun Jog, Po-Ling Loh
We study the problem of finding the maximum of a function defined on the nodes of a connected graph. The goal is to identify a node where the function obtains its maximum. We focus…
On Consistency of Compressive Spectral Clustering
Muni Sreenivas Pydi, Ambedkar Dukkipati
Spectral clustering is one of the most popular methods for community detection in graphs. A key step in spectral clustering algorithms is the eigen decomposition of the $n{\times}n…
Analytic Connectivity in General Hypergraphs
Ashwin Guha, Muni Sreenivas Pydi, Biswajit Paria +1
In this paper we extend the known results of analytic connectivity to non-uniform hypergraphs. We prove a modified Cheeger's inequality and also give a bound on analytic connectivi…