activity
20182022
most citedThe Geometry of Sign Gradient Descent

8 citations · 16 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG20201 cited

Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering

Ricky T. Q. Chen, Dami Choi, Lukas Balles +2

Standard first-order stochastic optimization algorithms base their updates solely on the average mini-batch gradient, and it has been shown that tracking additional quantities such…

cs.LG20208 cited

The Geometry of Sign Gradient Descent

Lukas Balles, Fabian Pedregosa, Nicolas Le Roux

Sign-based optimization methods have become popular in machine learning due to their favorable communication cost in distributed optimization and their surprisingly good performanc…

cs.LG2019

Limitations of the Empirical Fisher Approximation for Natural Gradient Descent

Frederik Kunstner, Lukas Balles, Philipp Hennig

Natural gradient descent, which preconditions a gradient descent update with the Fisher information matrix of the underlying statistical model, is a way to capture partial second-o…

cs.LG20196 cited

DeepOBS: A Deep Learning Optimizer Benchmark Suite

Frank Schneider, Lukas Balles, Philipp Hennig

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet,…

cs.CV2018

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

Anurag Ranjan, Varun Jampani, Lukas Balles +4

We address the unsupervised learning of several interconnected problems in low-level vision: single view depth prediction, camera motion estimation, optical flow, and segmentation…