Gradient Descent Can Take Exponential Time to Escape Saddle Points - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Simon S. Du, Chi Jin, Jason D. Lee, Michael I. Jordan, Aarti Singh, Barnabás Póczos. Gradient Descent Can Take Exponential Time to Escape Saddle Points. In Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, Roman Garnett, editors, Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA. pages 1067-1077, 2017. [doi]

This author has not been identified. Look up 'Simon S. Du' in GoogleThis author has not been identified. Look up 'Chi Jin' in GoogleThis author has not been identified. Look up 'Jason D. Lee' in GoogleThis author has not been identified. Look up 'Michael I. Jordan' in GoogleThis author has not been identified. Look up 'Aarti Singh' in GoogleThis author has not been identified. Look up 'Barnabás Póczos' in Google

runs on WebDSL