- 3:00pm, Tuesday, September 22th: Dejan Slepčev, An introduction to variational problems on graphs and their consistency, Slides
- 3:00pm, Tuesday, September 29th: Sangmin Park, Graph Laplacians and their continuum limit, Slides
- 3:00pm, Tuesday, October 13th: Raghav Venkatraman, Higher order derivatives on graphs, how they control continuity, and applications to semi-supervised learning
- 3:00pm, Tuesday, October 20th or 20th: Son Van Spectral consistency of the Graph Laplacian in Holder spaces, Slides
- 3:00pm, Tuesday, October 27th: Dejan Slepčev, Introduction to Stein Variational Descent and related topics, Slides
- 3:00pm, Tuesday, November 3rd: Lantian Xu, Introduction to Stein discrepancy and its applications , Slides
- 3:00pm, Tuesday, November 17th: Won Eui Hong, Geometry of Stein variational descent, Slides
- 3:00pm, Tuesday, December 1st: Andrew Warren, SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence, Slides
- Calder, Lecture Notes, Chapter 5
- Calder and Garcia Trillos Improved spectral convergence rates for graph Laplacians on epsilon-graphs and k-NN graphs, arXiv:1910.13476
- Calder, Garcia Trillos, and Lewicka Lipschitz regularity of graph Laplacians on random data clouds, arXiv:2007.06679
- Duncan, Nuesken and Szpruch, On the geometry of Stein variational gradient descent, arXiv:1912.00894
- Dunlop, Slepcev, Stuart, and Thorpe Large data and zero noise limits of graph-based semi-supervised learning algorithms, arXiv:1805.09450
- Maoutsa, Reich, Opper, Interacting particle solutions of Fokker–Planck equations through gradient–log–density estimation, arXiv:2006.00702
- Lu, Lu, A Universal Approximation Theorem of Deep Neural Networks for Expressing Distributions, arxiv:2004.08867
- Liu, Lee, Jordan, A Kernelized Stein Discrepancy for Goodness-of-fit Tests, arxiv:1602.03253.pdf
- Chewi, Gouic, Lu, Maunu, Rigollet, SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence, arxiv:2006.02509.pdf