Uri Shaham

Common Variable Learning and Invariant RepresentationLearning using Siamese Neural Networks

2015 · arXiv (Cornell University)

We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach …

Differentiable Unsupervised Feature Selection based on a Gated Laplacian

2020 · arXiv (Cornell University)

Scientific observations may consist of a large number of variables (features). Identifying a subset of meaningful features is often ignored in unsupervised learning, despite its potential for unraveling clear patterns hidden in the ambient space. …

What Do You Get When You Cross Beam Search with Nucleus Sampling?

2021 · arXiv (Cornell University)

We combine beam search with the probabilistic pruning technique of nucleus sampling to create two deterministic nucleus search algorithms for natural language generation. The first algorithm, p-exact search, locally prunes the next-token distribution and performs …