Related papers: NOCTA: Non-Greedy Objective Cost-Tradeoff Acquisit…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

Test-Time Adaptation (TTA) enables pre-trained models to adjust to distribution shift by learning from unlabeled test-time streams. However, existing methods typically treat these streams as independent samples, overlooking the supervisory…

We propose a model for making data acquisition decisions for variables in contextual stochastic optimisation problems. Data acquisition decisions are typically treated as separate and fixed. We explore problem settings in which the…

Machine learning methods often assume that input features are available at no cost. However, in domains like healthcare, where acquiring features could be expensive or harmful, it is necessary to balance a feature's acquisition cost against…

This study addresses the actual behavior of the credit-card fraud detection environment where financial transactions containing sensitive data must not be amassed in an enormous amount to conduct learning. We introduce a new adaptive…

Open-vocabulary object detection often fails under distribution shifts, as it can be misled by spurious correlations between non-causal visual attributes (e.g., brightness, texture) and object categories. Existing test-time adaptation (TTA)…

Slow concept drift is a ubiquitous, yet under-studied problem in practical machine learning systems. In such settings, although recent data is more indicative of future data, naively prioritizing recent instances runs the risk of losing…

Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly focus on model-based adaptation in a self-training manner, such…

Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gather valuable information about the state of the world for…

We propose a new, generic and flexible methodology for nonparametric function estimation, in which we first estimate the number and locations of any features that may be present in the function, and then estimate the function parametrically…

The goal of continuous emotion recognition is to assign an emotion value to every frame in a sequence of acoustic features. We show that incorporating long-term temporal dependencies is critical for continuous emotion recognition tasks. To…

This paper introduces temporally local metrics for Multi-Object Tracking. These metrics are obtained by restricting existing metrics based on track matching to a finite temporal horizon, and provide new insight into the ability of trackers…

Inverse optimal control (IOC) aims to estimate the underlying cost that governs the observed behavior of an expert system. However, in practical scenarios, the collected data is often corrupted by noise, which poses significant challenges…

Test-time adaptation (TTA) has emerged as a viable solution to adapt pre-trained models to domain shifts using unlabeled test data. However, TTA faces challenges of adaptation failures due to its reliance on blind adaptation to unknown test…

Combining multi-site data can strengthen and uncover trends, but is a task that is marred by the influence of site-specific covariates that can bias the data and therefore any downstream analyses. Post-hoc multi-site correction methods…

Constructing decision trees online is a classical machine learning problem. Existing works often assume that features are readily available for each incoming data point. However, in many real world applications, both feature values and the…

Maximizing long-term rewards is the primary goal in sequential decision-making problems. The majority of existing methods assume that side information is freely available, enabling the learning agent to observe all features' states before…

Multiple object tracking (MOT) involves identifying multiple targets and assigning them corresponding IDs within a video sequence, where occlusions are often encountered. Recent methods address occlusions using appearance cues through…

Many tasks in explainable machine learning, such as data valuation and feature attribution, perform expensive computation for each data point and are intractable for large datasets. These methods require efficient approximations, and…

3D Single Object Tracking (3D-SOT) aims to localize a target object across a sequence of LiDAR point clouds, given its 3D bounding box in the first frame. Recent methods have adopted a memory-based approach to utilize previously observed…