While the Evidence Lower Bound (ELBO) has become a ubiquitous objective for variational inference, the recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a tighter and more general family of bounds.
The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks.
In this short note I restate and simplify the proof of the impossibility of probabilistic induction from Popper (1992).
Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometric average.
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distributions between a tractable base and an unnormalized target.
Achieving the full promise of the Thermodynamic Variational Objective (TVO), a recently proposed variational lower bound on the log evidence involving a one-dimensional Riemann integral approximation, requires choosing a "schedule" of sorted discretization points.
We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training.
1 code implementation • 30 Mar 2020 • Frank Wood, Andrew Warrington, Saeid Naderiparizi, Christian Weilbach, Vaden Masrani, William Harvey, Adam Scibior, Boyan Beronov, John Grefenstette, Duncan Campbell, Ali Nasseri
In this work we demonstrate how to automate parts of the infectious disease-control policy-making process via performing inference in existing epidemiological models.
Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data.
Ranked #2 on Few-Shot Image Classification on Mini-Imagenet 10-way (1-shot) (using extra training data)
We investigate if writers with dementia can be automatically distinguished from those without by analyzing linguistic markers in written text, in the form of blog posts.