Sign up to receive the latest Insights posts in your inbox.

  • Data Science

JSM 2017 Experiences

A group of Two Sigma statisticians highlight a selection of interesting talks and presentations from the 2017 Joint Statistical Meeting.

  • Data Science
  • Technology

A Workaround for Non-Determinism in TensorFlow

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.

  • Data Science

Rademacher Averages: Theory and Practice

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.

  • Data Science

NIPS 2016: A Survey of Tutorials, Papers, and Workshops

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).

  • Data Science

Graph Summarization with Quality Guarantees

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.