Active learning for optimal intervention design in causal models
Sequential experimental design to discover interventions that achieve a desired outcome is
a key problem in various domains including science, engineering and public policy. When …
a key problem in various domains including science, engineering and public policy. When …
A Survey on Deep Active Learning: Recent Advances and New Frontiers
Active learning seeks to achieve strong performance with fewer training samples. It does this
by iteratively asking an oracle to label newly selected samples in a human-in-the-loop …
by iteratively asking an oracle to label newly selected samples in a human-in-the-loop …
Improving interpretability of deep active learning for flood inundation mapping through class ambiguity indices using multi-spectral satellite imagery
Flood inundation mapping is a critical task for responding to the increasing risk of flooding
linked to global warming. Significant advancements of deep learning in recent years have …
linked to global warming. Significant advancements of deep learning in recent years have …
Integrating Neural-Symbolic Reasoning With Variational Causal Inference Network for Explanatory Visual Question Answering
Recently, a novel multimodal reasoning task named Explanatory Visual Question Answering
(EVQA) has been introduced, which combines answering visual questions with multimodal …
(EVQA) has been introduced, which combines answering visual questions with multimodal …
Online decision mediation
Consider learning a decision support assistant to serve as an intermediary between (oracle)
expert behavior and (imperfect) human behavior: At each time, the algorithm observes an …
expert behavior and (imperfect) human behavior: At each time, the algorithm observes an …
Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes
Pool-based active learning (AL) is a promising technology for increasing data-efficiency of
machine learning models. However, surveys show that performance of recent AL methods is …
machine learning models. However, surveys show that performance of recent AL methods is …
Genedisco: A benchmark for experimental design in drug discovery
In vitro cellular experimentation with genetic interventions, using for example CRISPR
technologies, is an essential step in early-stage drug discovery and target validation that …
technologies, is an essential step in early-stage drug discovery and target validation that …
Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions
A Kirsch - arXiv preprint arXiv:2401.04305, 2024 - arxiv.org
At its core, this thesis aims to enhance the practicality of deep learning by improving the
label and training efficiency of deep learning models. To this end, we investigate data subset …
label and training efficiency of deep learning models. To this end, we investigate data subset …
Stochastic batch acquisition: A simple baseline for deep active learning
We examine a simple stochastic strategy for adapting well-known single-point acquisition
functions to allow batch active learning. Unlike acquiring the top-K points from the pool set …
functions to allow batch active learning. Unlike acquiring the top-K points from the pool set …
Sample constrained treatment effect estimation
Abstract Treatment effect estimation is a fundamental problem in causal inference. We focus
on designing efficient randomized controlled trials, to accurately estimate the effect of some …
on designing efficient randomized controlled trials, to accurately estimate the effect of some …