Related papers: Robust Learning via Conditional Prevalence Adjustm…

Dealing with severe class imbalance poses a major challenge for real-world applications, especially when the accurate classification and generalization of minority classes is of primary interest. In computer vision, learning from long…

Unsupervised Domain Adaptation (UDA) aims to adapt models from labeled source domains to unlabeled target domains. When adapting to adverse scenes, existing UDA methods fail to perform well due to the lack of instructions, leading their…

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

We introduce Causal Program Dependence Analysis (CPDA), a dynamic dependence analysis that applies causal inference to model the strength of program dependence relations in a continuous space. CPDA observes the association between program…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

Most pseudo-label selection strategies in semi-supervised learning rely on fixed confidence thresholds, implicitly assuming that prediction confidence reliably indicates correctness. In practice, deep networks are often overconfident:…

In-context learning for tabular data sets strong predictive standards in observational settings; it however primarily relies on correlational structure, which becomes unreliable under distribution shift or intervention. While established…

Many open problems in machine learning are intrinsically related to causality, however, the use of causal analysis in machine learning is still in its early stage. Within a general reinforcement learning setting, we consider the problem of…

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Recent Vision-Language-Action (VLA) models show strong generalization capabilities, yet they lack introspective mechanisms for anticipating failures and requesting help from a human supervisor. We present \textbf{INSIGHT}, a learning…

Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However,…

Identifying co-varying causal elements in very high dimensional feature space with internal structures, e.g., a space with as many as millions of linearly ordered features, as one typically encounters in problems such as whole genome…

Real-world deployment of machine learning models is challenging because data evolves over time. While no model can work when data evolves in an arbitrary fashion, if there is some pattern to these changes, we might be able to design methods…

Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking because they can both improve outcomes for study participants and increase the chance of identifying good or even…

In many applications, training machine learning models involves using large amounts of human-annotated data. Obtaining precise labels for the data is expensive. Instead, training with weak supervision provides a low-cost alternative. We…

Although much progress has been made towards robust deep learning, a significant gap in robustness remains between real-world perturbations and more narrowly defined sets typically studied in adversarial defenses. In this paper, we aim to…

Learning efficiently a causal model of the environment is a key challenge of model-based RL agents operating in POMDPs. We consider here a scenario where the learning agent has the ability to collect online experiences through direct…

PCA is a classical statistical technique whose simplicity and maturity has seen it find widespread use as an anomaly detection technique. However, it is limited in this regard by being sensitive to gross perturbations of the input, and by…

Causal inference and model interpretability research are gaining increasing attention, especially in the domains of healthcare and bioinformatics. Despite recent successes in this field, decorrelating features under nonlinear environments…