Related papers: Energy-Based Processes for Exchangeable Data
With the advent of cloud computing, organizations are nowadays able to react rapidly to changing demands for computational resources. Not only individual applications can be hosted on virtual cloud infrastructures, but also complete…
We develop a Bayesian non-parametric framework based on multi-task Gaussian processes, appropriate for temporal shrinkage. We focus on a particular class of dynamic hierarchical models to obtain evidence-based knowledge of infectious…
Building Information Modeling has been used to analyze as well as increase the energy efficiency of the buildings. It has shown significant promise in existing buildings by deconstruction and retrofitting. Current cities which were built…
Conditional Neural Processes~(CNPs) formulate distributions over functions and generate function observations with exact conditional likelihoods. CNPs, however, have limited expressivity for high-dimensional observations, since their…
We study the problem of learning associative memory -- a system which is able to retrieve a remembered pattern based on its distorted or incomplete version. Attractor networks provide a sound model of associative memory: patterns are stored…
Traditional scene graph generation methods are trained using cross-entropy losses that treat objects and relationships as independent entities. Such a formulation, however, ignores the structure in the output space, in an inherently…
Traditionally, business process management focuses on structured, imperative processes. With the increasing importance of knowledge work, semi-structured processes are entering center stage. Existing approaches to modeling…
Energy-based models for discrete domains, such as graphs, explicitly capture relative likelihoods, naturally enabling composable probabilistic inference tasks like conditional generation or enforcing constraints at test-time. However,…
Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving…
Environmentally-powered computer systems operate on renewable energy harvested from their environment, such as solar or wind, and stored in batteries. While harvesting environmental energy has long been necessary for small-scale embedded…
Measurement and analysis of high energetic particles for scientific, medical or industrial applications is a complex procedure, requiring the design of sophisticated detector and data processing systems. The development of adaptive and…
Many problems in Computer Science can be framed as the computation of queries over sequences, or "streams" of data units called events. The field of Complex Event Processing (CEP) relates to the techniques and tools developed to efficiently…
Energy-based models (EBMs) have gained popularity for controlled text generation due to their high applicability to a wide range of constraints. However, sampling from EBMs is non-trivial, as it often requires a large number of iterations…
Integration of variable energy resources -- e.g., solar, wind, and hydro -- and end-use electrification increase modern energy systems' weather-dependence. Identifying critical infrastructure constraining the power grid's ability to meet…
Evidence-Based Climate Policy (EBCP) is an approach to policymaking that relies on evidence to make decisions about managing climate impacts, mitigation, and adaptation. A core problem for EBCP is the lack of a clear definition of evidence,…
Edge Computing enables low-latency processing for real-time applications but introduces challenges in power management due to the distributed nature of edge devices and their limited energy resources. This paper proposes a stochastic…
Power flow calculation in EMS is required to accommodate a large and complex power system. To achieve a faster than real-time calculation, a graph based power flow calculation is proposed in this paper. Graph database and graph computing…
Buildings account for a substantial portion of global energy consumption. Reducing buildings' energy usage primarily involves obtaining data from building systems and environment, which are instrumental in assessing and optimizing the…
Benchmarks for the evaluation of model performance play an important role in machine learning. However, there is no established way to describe and create new benchmarks. What is more, the most common benchmarks use performance measures…
Intermediate-task transfer can benefit a wide range of NLP tasks with properly selected source datasets. However, it is computationally infeasible to experiment with all intermediate transfer combinations, making choosing a useful source…