Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
A major challenge in sample-based inference (SBI) for Bayesian neural networks is the size and structure of the networks' parameter space. Our work shows that successful SBI is possible by embracing the characteristic relationship between weight and function space, uncovering a systematic link between overparameterization and the difficulty of the sampling problem. Through extensive experiments, we establish practical guidelines for sampling and convergence diagnosis. As a result, we present a deep ensemble initialized approach as an effective solution with competitive performance and uncertainty quantification.
Code (1)
Tasks
Uncertainty QuantificationSimilar Papers 제목 키워드 기반
Interconnectedness in the Global Financial Market
The global financial system is highly complex, with cross-border interconnections and interdependencies. In this highly interconnected environment, local financial shocks and events can be easily amplified and turned int…
The Circle of Investment: Connecting the Dots of the Portfolio Management Cycle...
We will look at the entire cycle of the investment process relating to all aspects of, formulating an investment hypothesis, constructing a portfolio based on that, executing the trades to implement it, on-going risk man…
ManagementTotal, asymmetric and frequency connectedness between oil and forex markets
We analyze total, asymmetric and frequency connectedness between oil and forex markets using high-frequency, intra-day data over the period 2007 -- 2017. By employing variance decompositions and their spectral representa…
Connecting the Dots Between Fact Verification and Fake News Detection
Fact verification models have enjoyed a fast advancement in the last two years with the development of pre-trained language models like BERT and the release of large scale datasets such as FEVER. However, the challenging…
Fact VerificationFake News DetectionText SummarizationThe impact of external uncertainties on the extreme return connectedness between food, fossil energy, and clean energy markets
We investigate the extreme return connectedness between the food, fossil energy, and clean energy markets using the quantile connectedness approach, which combines the traditional spillover index with quantile regression…
CPUGPRquantile regression