research
∙
03/24/2022
Multi-armed bandits for online optimization of language model pre-training: the use case of dynamic masking
Transformer-based language models (TLMs) provide state-of-the-art perfor...
share
research
∙
02/24/2021
A generative, predictive model for menstrual cycle lengths that accounts for potential self-tracking artifacts in mobile health data
Mobile health (mHealth) apps such as menstrual trackers provide a rich s...
research
∙
09/24/2019
Characterizing physiological and symptomatic variation in menstrual cycles using self-tracked mobile health data
The menstrual cycle is a key indicator of overall health for women of re...
research
∙
08/27/2019
Multi-Task Gaussian Processes and Dilated Convolutional Networks for Reconstruction of Reproductive Hormonal Dynamics
We present an end-to-end statistical framework for personalized, accurat...
research
∙
11/06/2018
Phenotyping Endometriosis through Mixed Membership Models of Self-Tracking Data
We investigate the use of self-tracking data and unsupervised mixed-memb...
research
∙
08/08/2018
(Sequential) Importance Sampling Bandits
The multi-armed bandit (MAB) problem is a sequential allocation task whe...
research
∙
08/08/2018
Nonparametric Gaussian mixture models for the multi-armed contextual bandit
The multi-armed bandit is a sequential allocation task where an agent mu...
research
∙
11/30/2017
Towards Personalized Modeling of the Female Hormonal Cycle: Experiments with Mechanistic Models and Gaussian Processes
In this paper, we introduce a novel task for machine learning in healthc...
research
∙
09/10/2017
Variational inference for the multi-armed contextual bandit
In many biomedical, science, and engineering problems, one must sequenti...
research
∙
09/10/2017