Web: http://arxiv.org/abs/2111.05803

Jan. 24, 2022, 2:11 a.m. | Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz, Tal Kachman

cs.LG updates on arXiv.org arxiv.org

Differentiable programming techniques are widely used in the community and
are responsible for the machine learning renaissance of the past several
decades. While these methods are powerful, they have limits. In this short
report, we discuss a common chaos based failure mode which appears in a variety
of differentiable circumstances, ranging from recurrent neural networks and
numerical physics simulation to training learned optimizers. We trace this
failure to the spectrum of the Jacobian of the system under study, and provide …


Engineering Manager, Machine Learning (Credit Engineering)

@ Affirm | Remote Poland

Sr Data Engineer

@ Rappi | [CO] Bogotá

Senior Analytics Engineer

@ GetGround | Porto

Senior Staff Software Engineer, Data Engineering

@ Galileo, Inc. | New York City or Remote

Data Engineer

@ Atlassian | Bengaluru, India

Data Engineer | Hybrid (Pune)

@ Velotio | Pune, Maharashtra, India