Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein space

MZ Diao, K Balasubramanian… - … on Machine Learning, 2023 - proceedings.mlr.press
Variational inference (VI) seeks to approximate a target distribution $\pi $ by an element of a
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …

A survey of geometric optimization for deep learning: from Euclidean space to Riemannian manifold

Y Fei, Y Liu, C Jia, Z Li, X Wei, M Chen - ACM Computing Surveys, 2023 - dl.acm.org
Deep Learning (DL) has achieved remarkable success in tackling complex Artificial
Intelligence tasks. The standard training of neural networks employs backpropagation to …

[PDF][PDF] Statistical optimal transport

S Chewi, J Niles-Weed, P Rigollet - arXiv preprint arXiv:2407.18163, 2024 - arxiv.org
Statistical Optimal Transport arXiv:2407.18163v2 [math.ST] 7 Nov 2024 Page 1 Statistical
Optimal Transport Sinho Chewi Yale Jonathan Niles-Weed NYU Philippe Rigollet MIT …

Riemannian conjugate gradient methods: General framework and specific algorithms with convergence analyses

H Sato - SIAM Journal on Optimization, 2022 - SIAM
Conjugate gradient methods are important first-order optimization algorithms both in
Euclidean spaces and on Riemannian manifolds. However, while various types of conjugate …

The schrödinger bridge between gaussian measures has a closed form

C Bunne, YP Hsieh, M Cuturi… - … Conference on Artificial …, 2023 - proceedings.mlr.press
The static optimal transport $(\mathrm {OT}) $ problem between Gaussians seeks to recover
an optimal map, or more generally a coupling, to morph a Gaussian into another. It has been …

First-order algorithms for min-max optimization in geodesic metric spaces

M Jordan, T Lin… - Advances in Neural …, 2022 - proceedings.neurips.cc
From optimal transport to robust dimensionality reduction, many machine learning
applicationscan be cast into the min-max optimization problems over Riemannian manifolds …

Riemannian Hamiltonian methods for min-max optimization on manifolds

A Han, B Mishra, P Jawanpuria, P Kumar, J Gao - SIAM Journal on …, 2023 - SIAM
In this paper, we study min-max optimization problems on Riemannian manifolds. We
introduce a Riemannian Hamiltonian function, minimization of which serves as a proxy for …

Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems

M Giegrich, C Reisinger, Y Zhang - SIAM Journal on Control and Optimization, 2024 - SIAM
We study the global linear convergence of policy gradient (PG) methods for finite-horizon
continuous-time exploratory linear-quadratic control (LQC) problems. The setting includes …

Simplifying momentum-based positive-definite submanifold optimization with applications to deep learning

W Lin, V Duruisseaux, M Leok… - International …, 2023 - proceedings.mlr.press
Riemannian submanifold optimization with momentum is computationally challenging
because, to ensure that the iterates remain on the submanifold, we often need to solve …

Differentially private Riemannian optimization

A Han, B Mishra, P Jawanpuria, J Gao - Machine Learning, 2024 - Springer
In this paper, we study the differentially private empirical risk minimization problem where
the parameter is constrained to a Riemannian manifold. We introduce a framework for …