activity
20152022
most citedAn Investigation into Neural Net Optimization via Hessian Eigenvalue Density

103 citations · 166 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG202217 cited

Do Current Multi-Task Optimization Methods in Deep Learning Even Help?

Derrick Xin, Behrooz Ghorbani, Ankush Garg +2

Recent research has proposed a series of specialized optimization algorithms for deep multi-task models. It is often claimed that these multi-task optimization (MTO) methods yield…

cs.LG20228 cited

Data Scaling Laws in NMT: The Effect of Noise and Architecture

Yamini Bansal, Behrooz Ghorbani, Ankush Garg +5

In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT). First, we establish that…

cs.LG20216 cited

A Loss Curvature Perspective on Training Instability in Deep Learning

Justin Gilmer, Behrooz Ghorbani, Ankush Garg +6

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics.…

cs.LG202119 cited

Scaling Laws for Neural Machine Translation

Behrooz Ghorbani, Orhan Firat, Markus Freitag +5

We present an empirical study of scaling properties of encoder-decoder Transformer models used in neural machine translation (NMT). We show that cross-entropy loss as a function of…

cs.LG2019103 cited

An Investigation into Neural Net Optimization via Hessian Eigenvalue Density

Behrooz Ghorbani, Shankar Krishnan, Ying Xiao

To understand the dynamics of optimization in deep neural networks, we develop a tool to study the evolution of the entire Hessian spectrum throughout the optimization process. Usi…