From sets to multisets: provable variational inference for probabilistic integer submodular models

A Sahin, Y Bian, J Buhmann… - … Conference on Machine …, 2020 - proceedings.mlr.press
Submodular functions have been studied extensively in machine learning and data mining.
In particular, the optimization of submodular functions over the integer lattice (integer …

Testing, Learning, and Optimization in High Dimensions

K Gatmiry - 2022 - dspace.mit.edu
In this thesis we study two separate problems:(1) What is the sample complexity of testing
the class of Determinantal Point Processes? and (2) Introducing a new analysis for …

Testing determinantal point processes

K Gatmiry, M Aliakbarpour… - Advances in Neural …, 2020 - proceedings.neurips.cc
Determinantal point processes (DPPs) are popular probabilistic models of diversity. In this
paper, we investigate DPPs from a new perspective: property testing of distributions. Given …

[PDF][PDF] Integer Submodular Maximization: Algorithms and Modeling

A Sahin - 2022 - research-collection.ethz.ch
Submodular set functions are widely used in discrete optimization, machine learning and
computer vision because of their attractive properties in modeling and optimization. Despite …

Sampling from Probabilistic Submodular Models

A Gotovos - 2019 - research-collection.ethz.ch
Practical problems of discrete nature are very common in machine learning; application
domains include computer vision (eg, image segmentation), sequential decision making (eg …