Publications (6)
Parallel Streaming Wasserstein Barycenters
Matthew Staib, Sebastian Claici, Justin Solomon +1
Efficiently aggregating data from different sources is a challenging problem, particularly when samples from each source are distributed differently. These differences can be inher…
Robust Budget Allocation via Continuous Submodular Functions
Matthew Staib, Stefanie Jegelka
The optimal allocation of resources for maximizing influence, spread of information or coverage, has gained attention in the past years, in particular in machine learning and data…
Escaping Saddle Points with Adaptive Gradient Methods
Matthew Staib, Sashank J. Reddi, Satyen Kale +2
Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their…
Distributionally Robust Optimization and Generalization in Kernel Methods
Matthew Staib, Stefanie Jegelka
Distributionally robust optimization (DRO) has attracted attention in machine learning due to its connections to regularization, generalization, and robustness. Existing work has c…
Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks
Edward Kim, Zach Jensen, Alexander van Grootel +8
Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experime…
Distributionally Robust Submodular Maximization
Matthew Staib, Bryan Wilder, Stefanie Jegelka
Submodular functions have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function . We focus on stochastic functi…