Related papers: Variational Counterfactual Prediction under Runtim…

Training a policy in a source domain for deployment in the target domain under a dynamics shift can be challenging, often resulting in performance degradation. Previous work tackles this challenge by training on the source domain with…

Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…

Classical machine learning assumes that the training and test sets come from the same distributions. Therefore, a model learned from the labeled training data is expected to perform well on the test data. However, This assumption may not…

In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of general cross-domain visual recognition problems. To address…

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the original source dataset…

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one…

Empirical risk minimization often performs poorly when the distribution of the target domain differs from those of source domains. To address such potential distribution shifts, we develop an unsupervised domain adaptation approach that…

Increasingly, human behavior is captured on mobile devices, leading to an increased interest in automated human activity recognition. However, existing datasets typically consist of scripted movements. Our long-term goal is to perform…

We study robust mean estimation in an online and distributed scenario in the presence of adversarial data attacks. At each time step, each agent in a network receives a potentially corrupted data point, where the data points were originally…

Adversarial examples reveal the blind spots of deep neural networks (DNNs) and represent a major concern for security-critical applications. The transferability of adversarial examples makes real-world attacks possible in black-box…

Domain Adaptation arises when we aim at learning from source domain a model that can per- form acceptably well on a different target domain. It is especially crucial for Natural Language Generation (NLG) in Spoken Dialogue Systems when…

Large pre-trained models are usually fine-tuned on downstream task data, and tested on unseen data. When the train and test data come from different domains, the model is likely to struggle, as it is not adapted to the test domain. We…

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with…

The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. While there do exist…

Domain Adaptation is an actively researched problem in Computer Vision. In this work, we propose an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. We…

Standard supervised machine learning assumes that the distribution of the source samples used to train an algorithm is the same as the one of the target samples on which it is supposed to make predictions. However, as any data scientist…

Determining causal effects of interventions onto outcomes from real-world, observational (non-randomized) data, e.g., treatment repurposing using electronic health records, is challenging due to underlying bias. Causal deep learning has…

Randomized experiments have become a cornerstone of evidence-based decision-making in contexts ranging from online platforms to public health. However, in experimental settings with network interference, a unit's treatment can influence…

Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…

This paper considers identification and estimation of causal effect parameters from participating in a binary treatment in a difference in differences (DID) setup when the parallel trends assumption holds after conditioning on observed…