706 citations · 749 across the 20 of their papers we have counts for
10 papers · 1 filter
A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models
Nima Eshraghi, Lovedeep Gondara, Yuqing Huang +5
Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering si…
Supervised Learning Objectives for High-Dimensional Treatment Effects
Nikita Dhawan, Arnav Paruthi, Andrew Kim +3
Predicting the effect of interventions with many possible variations, e.g., therapeutic content that affects mental health outcomes or an earnings call transcript that drives movem…
Differentially Private Ensemble Classifiers for Data Streams
Lovedeep Gondara, Ke Wang, Ricardo Silva Carvalho
Learning from continuous data streams via classification/regression is prevalent in many domains. Adapting to evolving data characteristics (concept drift) while protecting data ow…
The Differentially Private Lottery Ticket Mechanism
Lovedeep Gondara, Ke Wang, Ricardo Silva Carvalho
We propose the differentially private lottery ticket mechanism (DPLTM). An end-to-end differentially private training paradigm based on the lottery ticket hypothesis. Using "high-q…
Differentially Private Survival Function Estimation
Lovedeep Gondara, Ke Wang
Survival function estimation is used in many disciplines, but it is most common in medical analytics in the form of the Kaplan-Meier estimator. Sensitive data (patient records) is…
Recovering Loss to Followup Information Using Denoising Autoencoders
Lovedeep Gondara, Ke Wang
Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost. Methods available at present for recovering loss to followup inf…
MIDA: Multiple Imputation using Denoising Autoencoders
Lovedeep Gondara, Ke Wang
Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputati…
Detecting Adversarial Samples Using Density Ratio Estimates
Lovedeep Gondara
Machine learning models, especially based on deep architectures are used in everyday applications ranging from self driving cars to medical diagnostics. It has been shown that such…
CrowdMI: Multiple Imputation via Crowdsourcing
Lovedeep Gondara
Can humans impute missing data with similar proficiency as machines? This is the question we aim to answer in this paper. We present a novel idea of converting observations with mi…
Classifier comparison using precision
Lovedeep Gondara
New proposed models are often compared to state-of-the-art using statistical significance testing. Literature is scarce for classifier comparison using metrics other than accuracy.…