Related papers: Targeted learning: Towards a future informed by re…
We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single…
Randomized controlled trials (RCTs) are increasingly prevalent in education research, and are often regarded as a gold standard of causal inference. Two main virtues of randomized experiments are that they (1) do not suffer from…
Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient…
Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two major constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning,…
Two-way fixed effects (TWFE) models are widely used in political science to establish causality, but recent methodological discussions highlight their limitations under heterogeneous treatment effects (HTE) and violations of the parallel…
World models predict state transitions in response to actions and are increasingly developed across diverse modalities. However, standard training objectives such as maximum likelihood estimation (MLE) often misalign with task-specific…
In this work, we address the problem of determining reliable policies in reinforcement learning (RL), with a focus on optimization under uncertainty and the need for performance guarantees. While classical RL algorithms aim at maximizing…
In this work, we present our various contributions to the objective of building a decision support tool for the diagnosis of rare diseases. Our goal is to achieve a state of knowledge where the uncertainty about the patient's disease is…
Longitudinal MRIs are often used to capture the gradual deterioration of brain structure and function caused by aging or neurological diseases. Analyzing this data via machine learning generally requires a large number of ground-truth…
The rapid digitization of real-world data presents an unprecedented opportunity to optimize healthcare delivery and accelerate biomedical discovery. However, these data are often found in unstructured forms such as clinical notes in…
Reinforcement learning (RL) in robotics is often limited by the cost and risk of data collection, motivating experience transfer from a source task to a target task. Offline-to-online RL leverages prior data but typically assumes a given…
Autonomous driving in urban crowds at unregulated intersections is challenging, where dynamic occlusions and uncertain behaviors of other vehicles should be carefully considered. Traditional methods are heuristic and based on…
Many diagnostic errors occur because clinicians cannot easily access relevant information in patient Electronic Health Records (EHRs). In this work we propose a method to use LLMs to identify pieces of evidence in patient EHR data that…
This paper investigates a novel nonlinear update rule based on temporal difference (TD) errors in reinforcement learning (RL). The update rule in the standard RL states that the TD error is linearly proportional to the degree of updates,…
Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…
Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human…
Why does a phenomenon occur? Addressing this question is central to most scientific inquiries and often relies on simulations of scientific models. As models become more intricate, deciphering the causes behind phenomena in high-dimensional…
Training deep neural networks requires many training samples, but in practice, training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…
Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools can mitigate this issue, models fine-tuned on tool usage…
Attention-based sequential recommendation methods have shown promise in accurately capturing users' evolving interests from their past interactions. Recent research has also explored the integration of reinforcement learning (RL) into these…