This page is no longer being maintained. Please refer to my webpage https://lballes.github.io.

About Me

I am a Ph.D. student in the Probabilistic Numerics Group, where I work on optimization methods for machine learning. Optimization algorithms are the workhorse of contemporary machine learning - it's where the numbers are crunched! Intriguingly, numerical optimizers themselves are compact little "learning machines": they make decisions (where to evaluate next, how many and which data points to use) based on observations (function values and gradients, typically corrupted by noise due to mini-batch subsampling). My goal is to design smarter optimizers!

Currently, my work centers around estimating the stochastic gradient variance, a measure for how "noisy" stochastic gradients are. I believe that using this quantity to make optimizers aware of the stochasticity of their evaluations can help improve various aspects of stochastic optimization algorithms. For example, gradient variance estimates can be used to adaptively choose "good" batch sizes when performing stochastic gradient descent [ ]. Element-wise variance estimates can also be used to manipulate the search direction itself by "damping" coordinate directions with low signal-to-noise ratio [ ].

Prior to joining the Max Planck Institute as a Ph.D. student, I studied Mathematics (B.Sc.) and Scientific Computing (M.Sc.) at Heidelberg University and spent some time as a visiting student at Tsinghua University in Beijing.