In the machine learning research community, it is generally believed that there is a tension between memorization and generalization. This paper examines the extent to which this tension exists, by exploring whether it is possible to generalize by memorizing alone.
A senior Two Sigma researcher provides an overview of some of the most interesting Deep Learning research from ICML 2017.
A group of Two Sigma statisticians highlight a selection of interesting talks and presentations from the 2017 Joint Statistical Meeting.
Two Sigma Co-founder and Co-chairman David Siegel offers his views on these topics and more at Bloomberg’s Sooner Than You Think conference.
The authors present TRIÈST, a suite of one-pass streaming algorithms to compute unbiased, low-variance, high-quality approximations of the global and local number of triangles in a fully-dynamic graph represented as an adversarial stream of edge insertions and deletions.
Speed and repeatability are crucial in machine learning, but the latter is not guaranteed in TensorFlow. A Two Sigma researcher demonstrates a workaround to attain repeatable results.
An overview of Rademacher Averages, a fundamental concept from statistical learning theory that can be used to derive uniform sample-dependent bounds to the deviation of samples averages from their expectations.
Two Sigma researchers discuss notable advances in deep learning, optimization algorithms, Bayesian techniques, and time-series analysis presented at 2016's Conference on Neural Information Processing Systems (NIPS).
Given a large graph, the authors we aim at producing a concise lossy representation (a summary) that can be stored in main memory and used to approximately answer queries about the original graph much faster than by using the exact representation.
Cook, Two Sigma’s open-source resource scheduler for compute clusters, uses preemption to achieve low latency and high throughput.