4 accepted papers
Contrastive learning is often trained with the InfoNCE loss, which uses a softmax over similarities to make the positive pair score higher than many negatives. Beyond its connection to mutual information, this softmax link has a precise probabilistic meaning: it is the maximum likelihood objective o…
Computing eigenvalue decomposition (EVD) of a given linear operator, or finding its leading eigenvalues and eigenfunctions, is a fundamental task in many machine learning and scientific simulation problems. For high-dimensional eigenvalue problems, training neural networks to parameterize the eigenf…
Current transfer learning algorithm designs mainly focus on the similarities between source and target tasks, while the impacts of the sample sizes of these tasks are often not sufficiently addressed. This paper proposes a mathematical framework for quantifying the transferability in multi-source tr…
We propose a non-adaptive unequal error protection (UEP) querying policy based on superposition coding for the noisy 20 questions problem. In this problem, a player wishes to successively refine an estimate of the value of a continuous random variable by posing binary queries and receiving noisy res…