arXiv research

Method maps imperfect simulations to observed stellar spectra using unsupervised domain adaptation.

Agents learning to act autonomously in real-world domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing …

Generates counterfactuals in target domain from source domain observations.

HIP-GP improves GP inference for inter-domain observations with millions of inducing points.

Hybrid framework merges data and domain knowledge for better spatial interpolation.

New method improves domain generalization by matching object representations.

In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven prediction methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to …

The paper explains how data augmentation can improve domain generalization by weakening spurious correlations.

Choosing optimal (or at least better) policies is an important problem in domains from medicine to education to finance and many others. One approach to this problem is through controlled experiments/trials - but controlled experiments are expensive. Hence it is important to choose the best policies on the basis of obs…

The paper analyzes the stability of an observer error in a vibrating string system.

Dual-structured method improves cross-domain imitation learning.

Method learns domain-specific representations without supervision.

In this paper, we consider infinite-dimensional port-Hamiltonian systems with in-domain actuation by means of an approach based on Stokes-Dirac structures as well as in a framework that exploits an underlying jet-bundle structure. In both frameworks, a dynamic controller based on the energy-Casimir method is derived in…

Unpaired multi-domain causal representation learning is possible with sufficient conditions.

Paper establishes baselines for offline RL from visual observations.

Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architectu…

Paper introduces Influence Function to assess OOD generalization stability.

Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e.g., computer Go. However, very little work has been done in deep RL to handle partially observable environments. We propose a new architec…

New method identifies stable latent variables across different domains using weak distributional invariances.

Many interesting real world domains involve reinforcement learning (RL) in partially observable environments. Efficient learning in such domains is important, but existing sample complexity bounds for partially observable RL are at least exponential in the episode length. We give, to our knowledge, the first partially …

State representation learning (SRL) in partially observable Markov decision processes has been studied to learn abstract features of data useful for robot control tasks. For SRL, acquiring domain-agnostic states is essential for achieving efficient imitation learning. Without these states, imitation learning is hampere…

Paper tackles sim-to-real transfer in continuous domains with partial observations.

ContraBAR uses contrastive learning to learn Bayes-optimal policies in RL.

Proposes MR-SNE for multimodal data visualization.

Bayesian model reconstructs time and frequency data robustly.

Adapts to shifts in latent subgroup distributions without labeled target data.

DAPDAG learns DAG structure to adapt predictions across domains.

Proposes a new approach for domain adaptation using latent representations.

Transfer learning framework for fragility modeling under domain shift and class imbalance

Generates samples conditioned on labels using optimal transport.

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain …

Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…

Framework integrates mental disorder measurements for personalized treatment.

Medical imaging systems are commonly assessed by use of objective image quality measures. Supervised deep learning methods have been investigated to implement numerical observers for task-based image quality assessment. However, labeling large amounts of experimental data to train deep neural networks is tedious, expen…

Proposes a method to adapt to new classes in a domain shift.

We consider a Laplace eigenfunction $\varphi_λ$ on a smooth closed Riemannian manifold, that is, satisfying $-Δ\varphi_λ= λ\varphi_λ$. We introduce several observations about the geometry of its vanishing (nodal) set and corresponding nodal domains. First, we give asymptotic upper and lower bounds on the volume of a tu…

UDA improves ABI robustness but fails under certain prior misspecifications.

Proposes DFDG for robust domain generalization without source domain labels.

We first study holomorphic isometries from the Poincaré disk into the product of the unit disk and the complex unit $n$-ball for $n\ge 2$. On the other hand, we observe that there exists a holomorphic isometry from the product of the unit disk and the complex unit $n$-ball into any irreducible bounded symmetric domain …

In this work, we present an interesting attempt on mixture generation: absorbing different image concepts (e.g., content and style) from different domains and thus generating a new domain with learned concepts. In particular, we propose a mixture generative adversarial network (MIXGAN). MIXGAN learns concepts of conten…

New families of non-tiling domains satisfy Pólya's conjecture.

A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional dist…

New method improves domain generalization by aligning causal mechanisms across domains.

Domain adaptation has become a prominent problem setting in machine learning and related fields. This review asks the question: how can a classifier learn from a source domain and generalize to a target domain? We present a categorization of approaches, divided into, what we refer to as, sample-based, feature-based and…

Cisco introduces a new time series model for better forecasting.

In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN). By exploiting the observation that a convolutional filter can be well approximated as a linear combination of a small set of dict…

New challenges in causal inference with big data.

Causal inference is similar to prediction with treatment bias.