Related papers: Synergizing Deconfounding and Temporal Generalizat…

Multi-contrast MRI acquisitions of an anatomy enrich the magnitude of information available for diagnosis. Yet, excessive scan times associated with additional contrasts may be a limiting factor. Two mainstream approaches for enhanced scan…

Graph-based learning excels at capturing interaction patterns in diverse domains like recommendation, fraud detection, and particle physics. However, its performance often degrades under distribution shifts, especially those altering…

Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the disentanglement and estimation of multiple treatment effects…

In decision-making processes, stakeholders often rely on counterfactual explanations, which provide suggestions about what should be changed in the queried instance to alter the outcome of an AI system. However, generating these…

Multiple sclerosis (MS) expresses substantial clinical and radiological heterogeneity, which poses significant challenges for automatic lesion segmentation. The current deep learning-based SOTA is highly susceptible to changes in both…

Causal inference on time series data is a challenging problem, especially in the presence of unobserved confounders. This work focuses on estimating the causal effect between two time series that are confounded by a third, unobserved time…

We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have…

Data scarcity and discontinuity are common occurrences in the healthcare and epidemiological dataset and often need help in forming an educative decision and forecasting the upcoming scenario. Often, these data are stored as monthly/yearly…

In large-scale distributed machine learning, recent works have studied the effects of compressing gradients in stochastic optimization to alleviate the communication bottleneck. These works have collectively revealed that stochastic…

Anomaly detection of multivariate time series is meaningful for system behavior monitoring. This paper proposes an anomaly detection method based on unsupervised Short- and Long-term Mask Representation learning (SLMR). The main idea is to…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal…

Researchers are often interested in using longitudinal data to estimate the causal effects of hypothetical time-varying treatment interventions on the mean or risk of a future outcome. Standard regression/conditioning methods for…

We study a new model where the potential outcomes, corresponding to the values of a (possibly continuous) treatment, are linked through common factors. The factors can be estimated using a panel of regressors. We propose a procedure to…

With the uptake of targeted therapies, instead of the "one-fits-all" approach, modern randomized clinical trials (RCTs) often aim to develop treatments that target a subgroup of patients. Motivated by analyzing the Age-Related Eye Disease…

In our article, we describe a method for generating counterfactual explanations in high-dimensional spaces using four steps that involve fitting our dataset to a model, finding the decision boundary, determining constraints on the problem,…

A critical challenge for any intelligent system is to infer structure from continuous data streams. Theories of event-predictive cognition suggest that the brain segments sensorimotor information into compact event encodings, which are used…

Diffusion large language models (dLLMs) generate text through iterative denoising, yet current decoding strategies discard rich intermediate predictions in favor of the final output. Our work here reveals a critical phenomenon, temporal…

Survival Analysis (SA) constitutes the default method for time-to-event modeling due to its ability to estimate event probabilities of sparsely occurring events over time. In this work, we show how to improve the training and inference of…

Although the rise of large language models (LLMs) has introduced new opportunities for time series forecasting, existing LLM-based solutions require excessive training and exhibit limited transferability. In view of these challenges, we…