2 papers
cs.LG2019
Differentiable Combinatorial Losses through Generalized Gradients of Linear Programs
Xi Gao, Han Zhang, Aliakbar Panahi +1
When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-seq…
cs.LG2019
Approximation Capabilities of Neural ODEs and Invertible Residual Networks
Han Zhang, Xi Gao, Jacob Unterman +1
Neural ODEs and i-ResNet are recently proposed methods for enforcing invertibility of residual neural models. Having a generic technique for constructing invertible models can open…