Shiqian Ma
@shiqianma.bsky.social
Professor at Rice University. Optimization and machine learning.
Two papers on bilevel optimization are published in JMLR. “Efficiently Escaping Saddle Points in Bilevel Optimization” and “Riemannian Bilevel Optimization” www.jmlr.org/papers/v26/2... www.jmlr.org/papers/v26/2...
Efficiently Escaping Saddle Points in Bilevel Optimization
www.jmlr.org
February 21, 2025 at 3:14 AM
Two papers on bilevel optimization are published in JMLR. “Efficiently Escaping Saddle Points in Bilevel Optimization” and “Riemannian Bilevel Optimization” www.jmlr.org/papers/v26/2... www.jmlr.org/papers/v26/2...
Our paper on tuning-free gradient method: “AdaBB: Adaptive Barzilai-Borwein Method for Convex Optimization” is accepted in Math of OR. arxiv.org/abs/2401.08024
AdaBB: Adaptive Barzilai-Borwein Method for Convex Optimization
In this paper, we propose AdaBB, an adaptive gradient method based on the Barzilai-Borwein stepsize. The algorithm is line-search-free and parameter-free, and essentially provides a convergent variant...
arxiv.org
February 21, 2025 at 3:11 AM
Our paper on tuning-free gradient method: “AdaBB: Adaptive Barzilai-Borwein Method for Convex Optimization” is accepted in Math of OR. arxiv.org/abs/2401.08024
Reposted by Shiqian Ma
New work on Riemannian Proximal Sampler, to sample on Riemannian manifolds:
arxiv.org/abs/2502.07265
Comes with high-accuracy (i.e., log(1/eps), where eps is tolerance) guarantees with exact and inexact oracles for Manifold Brownian Increments and Riemannian Heat-kernels
arxiv.org/abs/2502.07265
Comes with high-accuracy (i.e., log(1/eps), where eps is tolerance) guarantees with exact and inexact oracles for Manifold Brownian Increments and Riemannian Heat-kernels
Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds
We introduce the Riemannian Proximal Sampler, a method for sampling from densities defined on Riemannian manifolds. The performance of this sampler critically depends on two key oracles: the Manifold ...
arxiv.org
February 12, 2025 at 9:59 PM
New work on Riemannian Proximal Sampler, to sample on Riemannian manifolds:
arxiv.org/abs/2502.07265
Comes with high-accuracy (i.e., log(1/eps), where eps is tolerance) guarantees with exact and inexact oracles for Manifold Brownian Increments and Riemannian Heat-kernels
arxiv.org/abs/2502.07265
Comes with high-accuracy (i.e., log(1/eps), where eps is tolerance) guarantees with exact and inexact oracles for Manifold Brownian Increments and Riemannian Heat-kernels
Reposted by Shiqian Ma
We implement these oracles using heat-kernel truncation & Varadhan's asymptotics, linking our method to entropy-regularized proximal point method on Wasserstein spaces, in the latter case.
Joint work with Yunrui Guan and @shiqianma.bsky.social
Joint work with Yunrui Guan and @shiqianma.bsky.social
February 12, 2025 at 9:59 PM
We implement these oracles using heat-kernel truncation & Varadhan's asymptotics, linking our method to entropy-regularized proximal point method on Wasserstein spaces, in the latter case.
Joint work with Yunrui Guan and @shiqianma.bsky.social
Joint work with Yunrui Guan and @shiqianma.bsky.social
Our paper Riemannian Bilevel Optimization is accepted in Journal of Machine Learning Research! arxiv.org/abs/2402.02019
Riemannian Bilevel Optimization
In this work, we consider the bilevel optimization problem on Riemannian manifolds. We inspect the calculation of the hypergradient of such problems on general manifolds and thus enable the utilizatio...
arxiv.org
January 14, 2025 at 4:24 AM
Our paper Riemannian Bilevel Optimization is accepted in Journal of Machine Learning Research! arxiv.org/abs/2402.02019