paper-with-me

Papers

Implicit Riemannian Optimism with Applications to Min-Max Problems

2025-01-30 · Christophe Roux, David Martínez-Rubio, Sebastian Pokutta

We introduce a Riemannian optimistic online learning algorithm for Hadamard manifolds based on inexact implicit updates. Unlike prior work, our method can handle in-manifold constraints, and matches the best known regret bounds in the Euclidean setting with no dependence on geometric constants, like the minimum curvature. Building on this, we develop algorithms for g-convex, g-concave smooth min-max problems on Hadamard manifolds. Notably, one method nearly matches the gradient oracle complexity of the lower bound for Euclidean problems, for the first time.

📄 PDF Abstract BibTeX arXiv:2501.18381

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Implicit Riemannian Concave Potential Maps

2021-10-04 · Danilo J. Rezende, Sébastien Racanière

We are interested in the challenging problem of modelling densities on Riemannian manifolds with a known symmetry group using normalising flows. This has many potential applications in physical sciences such as molecular…

Density EstimationNormalising Flows

Riemannian adaptive stochastic gradient algorithms on matrix manifolds

2019-02-04 · Hiroyuki Kasai, Pratik Jawanpuria, Bamdev Mishra

Adaptive stochastic gradient algorithms in the Euclidean space have attracted much attention lately. Such explorations on Riemannian manifolds, on the other hand, are relatively new, limited, and challenging. This is bec…

Supervised Optimism Correction: Be Confident When LLMs Are Sure

2025-04-10 · Junjie Zhang, Rushuai Yang, Shunyu Liu, Ting-En Lin 외

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn…

GSM8KMathMathematical Reasoning

Landing with the Score: Riemannian Optimization through Denoising

2025-09-27 · Andrey Kharitenko, Zebang Shen, Riccardo de Santi, Niao He 외 arxiv

Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when they are given only implicitly through …

Block-Coordinate Minimization for Large SDPs with Block-Diagonal Constraints

2019-03-02 · Yulun Tian, Kasra Khosoussi, Jonathan P. How

The so-called Burer-Monteiro method is a well-studied technique for solving large-scale semidefinite programs (SDPs) via low-rank factorization. The main idea is to solve rank-restricted, albeit non-convex, surrogates in…

Riemannian optimization