6 papers
An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
Hoang Tran, Jorge Ramirez, Jiayi Wang +3
Fine-tuning adapts a pretrained machine learning model to a small, sensitive dataset, but this process risks memorizing individual new data points, making the model vulnerable to a…
State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
Hoang-Son Tran, Pranav Gupta, Rémi Bardenet +1
Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious…
Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
Subhroshekhar Ghosh, Adityanand Guntuboyina, Satyaki Mukherjee +1
In this work, we investigate Gaussian Mixture Models ({\it abbrv} GMM) and the related problem of non parametric maximum likelihood estimation ({\it abbrv} NPMLE) from the perspect…
Negative Dependence as a toolbox for machine learning : review and new developments
Hoang-Son Tran, Vladimir Petrovic, Remi Bardenet +1
Negative dependence is becoming a key driver in advancing learning capabilities beyond the limits of traditional independence. Recent developments have evidenced support towards ne…
Learning Networks from Gaussian Graphical Models and Gaussian Free Fields
Subhro Ghosh, Soumendu Sundar Mukherjee, Hoang-Son Tran +1
We investigate the problem of estimating the structure of a weighted network from repeated measurements of a Gaussian Graphical Model (GGM) on the network. In this vein, we conside…
Gaussian fluctuations for spin systems and point processes: near-optimal rates via quantitative Marcinkiewicz's theorem
Tien-Cuong Dinh, Subhroshekhar Ghosh, Hoang-Son Tran +1
We establish asymptotically Gaussian fluctuations for functionals of a large class of spin models and strongly correlated random point fields, achieving near-optimal rates. For spi…