paper-list
List of potential papers or topics to present (is this list a little ambitious? definitely)
High-dimensional statistics and probability theory
- Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem [PDF] (2019)
- Statistical optimal transport via factored couplings [PDF] (2018)
- Entropic optimal transport is maximum likelihood deconvolution [PDF] (2018)
- Minimax rates of estimation for smooth optimal transport maps [PDF] (2019)
- Overview of transportation inequalities (e.g. Chapter 4 of these lectures notes)
Wasserstein Gradient Flows and applications
- Overview of WGFs (e.g. Santambrogio)
- Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss [PDF] (2020)
- The Variational Formulation of the Fokker-Planck Equation [PDF] (1998)
- Gradient Flows in Wasserstein Spaces and Applications to Crowd Movement [PDF] (2009)
- On the Global Convergence of Gradient Descent for Over-parametrized Models using OT [PDF] (2019)
Applications in machine learning/deep learing/reinforcement learning
- How well do WGANs estimate the Wasserstein metric? [PDF] (2019)
- Policy Optimization as Wasserstein Gradient Flows [PDF] (2018)