We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval
Bayesian inference provides a natural way of incorporating prior beliefs and assigning a probability measure to the space of hypotheses. Cur… (see more)rent solutions rely on iterative routines like Markov Chain Monte Carlo (MCMC) sampling and Variational Inference (VI), which need to be re-run whenever new observations are available. Amortization, through conditional estimation, is a viable strategy to alleviate such difficulties and has been the guiding principle behind simulation-based inference, neural processes and in-context methods using pre-trained models. In this work, we conduct a thorough comparative analysis of amortized in-context Bayesian posterior estimation methods from the lens of different optimization objectives and architectural choices. Such methods train an amortized estimator to perform posterior parameter inference by conditioning on a set of data examples passed as context to a sequence model such as a transformer. In contrast to language models, we leverage permutation invariant architectures as the true posterior is invariant to the ordering of context examples. Our empirical study includes generalization to out-of-distribution tasks, cases where the assumed underlying model is misspecified, and transfer from simulated to real problems. Subsequently, it highlights the superiority of the reverse KL estimator for predictive problems, especially when combined with the transformer architecture and normalizing flows.
Bayesian inference provides a natural way of incorporating prior beliefs and assigning a probability measure to the space of hypotheses. Cur… (see more)rent solutions rely on iterative routines like Markov Chain Monte Carlo (MCMC) sampling and Variational Inference (VI), which need to be re-run whenever new observations are available. Amortization, through conditional estimation, is a viable strategy to alleviate such difficulties and has been the guiding principle behind simulation-based inference, neural processes and in-context methods using pre-trained models. In this work, we conduct a thorough comparative analysis of amortized in-context Bayesian posterior estimation methods from the lens of different optimization objectives and architectural choices. Such methods train an amortized estimator to perform posterior parameter inference by conditioning on a set of data examples passed as context to a sequence model such as a transformer. In contrast to language models, we leverage permutation invariant architectures as the true posterior is invariant to the ordering of context examples. Our empirical study includes generalization to out-of-distribution tasks, cases where the assumed underlying model is misspecified, and transfer from simulated to real problems. Subsequently, it highlights the superiority of the reverse KL estimator for predictive problems, especially when combined with the transformer architecture and normalizing flows.
Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generaliza… (see more)tion when faced with shifted testing distributions. To address this issue, various methods from imbalanced learning, representation learning, and classifier recalibration have been proposed to enhance the robustness of deep neural networks against spurious correlations. In this paper, we observe that models trained with empirical risk minimization tend to generalize well for examples from the majority groups while memorizing instances from minority groups. Building on recent findings that show memorization can be localized to a limited number of neurons, we apply example-tied dropout as a method we term FairDropout, aimed at redirecting this memorization to specific neurons that we subsequently drop out during inference. We empirically evaluate FairDropout using the subpopulation benchmark suite encompassing vision, language, and healthcare tasks, demonstrating that it significantly reduces reliance on spurious correlations, and outperforms state-of-the-art methods.
Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance l… (see more)evels comparable to the original models. In this work, we investigate the impact of quantization procedures on the privacy of data-driven models, specifically focusing on their vulnerability to membership inference attacks. We derive an asymptotic theoretical analysis of Membership Inference Security (MIS), characterizing the privacy implications of quantized algorithm weights against the most powerful (and possibly unknown) attacks. Building on these theoretical insights, we propose a novel methodology to empirically assess and rank the privacy levels of various quantization procedures. Using synthetic datasets, we demonstrate the effectiveness of our approach in assessing the MIS of different quantizers. Furthermore, we explore the trade-off between privacy and performance using real-world data and models in the context of molecular modeling.
Quantizing machine learning models has demonstrated its effectiveness in lowering memory and inference costs while maintaining performance l… (see more)evels comparable to the original models. In this work, we investigate the impact of quantization procedures on the privacy of data-driven models, specifically focusing on their vulnerability to membership inference attacks. We derive an asymptotic theoretical analysis of Membership Inference Security (MIS), characterizing the privacy implications of quantized algorithm weights against the most powerful (and possibly unknown) attacks. Building on these theoretical insights, we propose a novel methodology to empirically assess and rank the privacy levels of various quantization procedures. Using synthetic datasets, we demonstrate the effectiveness of our approach in assessing the MIS of different quantizers. Furthermore, we explore the trade-off between privacy and performance using real-world data and models in the context of molecular modeling.
BACKGROUND
Pediatric surgical care is limited in Afghanistan. Few details are known about the state of pediatric surgery in Afghanistan. We … (see more)explore the impact of a newly installed pediatric operating room by a children's charity on the provision of pediatric surgery in Afghanistan.
STUDY DESIGN
Following the opening in March 2023 of the new KidsOR operating room at Ataturk Hospital in Kabul, Afghanistan, perioperative clinical data was prospectively collected until December 2023. All children (age 14 years) undergoing surgical procedures were included in a REDCap database, and descriptive analyses were performed.
RESULTS
1,014 opera
2025-02-10
Journal of the American College of Surgeons (published)
Objective To build and validate a simulation framework to perform single-cell and bulk-cell whole genome sequencing simulation of radiation-… (see more)exposed Monte Carlo cell models to assist radiation genomics studies. Approach Sequencing the genomes of radiation-damaged cells can provide useful insight into radiation action for radiobiology research. However, carrying out post-irradiation sequencing experiments can often be challenging, expensive, and time-consuming. Although computational simulations have the potential to provide solutions to these experimental challenges, and aid in designing optimal experiments, the absence of tools currently limits such application. Monte Carlo toolkits exist to simulate radiation exposures of cell models but there are no tools to simulate single- and bulk-cell sequencing of cell models containing radiation-damaged DNA. Therefore, we aimed to develop a Monte Carlo simulation framework to address this gap by designing a tool capable of simulating sequencing processes for radiation-damaged cells. Main Results We developed RadiSeq – a multi-threaded whole-genome DNA sequencing simulator written in C++. RadiSeq can be used to simulate Illumina sequencing of radiation-damaged cell models produced by Monte Carlo simulations. RadiSeq has been validated through comparative analysis, where simulated data were matched against experimentally obtained data, demonstrating reasonable agreement between the two. Additionally, it comes with numerous features designed to closely resemble actual whole-genome sequencing. RadiSeq is also highly customizable with a single input parameter file. Significance RadiSeq enables the research community to perform complex simulations of radiation-exposed DNA sequencing, supporting the optimization, planning, and validation of costly and time-intensive radiation biology experiments. This framework provides a powerful tool for advancing radiation genomics research.
