"convergence guarantees" Papers

14 papers found

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

Yuchen Liang, Renxiang Huang, Lifeng LAI et al.

NEURIPS 2025arXiv:2506.02318
6
citations

AdaGrad under Anisotropic Smoothness

Yuxing Liu, Rui Pan, Tong Zhang

ICLR 2025arXiv:2406.15244
14
citations

A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning

Daniel Tschernutter, David Diego Castro, Maciej Kasiński

NEURIPS 2025

A Stochastic Approach to the Subset Selection Problem via Mirror Descent

Dan Greenstein, Elazar Gershuni, Ilan Ben-Bassat et al.

ICLR 2025

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

Yuchen Liang, Yingbin Liang, Lifeng LAI et al.

NEURIPS 2025arXiv:2509.16756
3
citations

Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems

Sayantan Choudhury, Nicolas Loizou

NEURIPS 2025arXiv:2510.22421

Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies

Vipul Sharma, Wesley Suttle, S Sivaranjani

NEURIPS 2025

MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization

Da Chang, Ganzhao Yuan

NEURIPS 2025spotlight

Understanding outer learning rates in Local SGD

Ahmed Khaled, Satyen Kale, Arthur Douillard et al.

NEURIPS 2025

Detecting Influence Structures in Multi-Agent Reinforcement Learning

Fabian Raoul Pieroth, Katherine Fitch, Lenz Belzner

ICML 2024

Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach

Vijay Keswani, Anay Mehrotra, L. Elisa Celis

ICML 2024arXiv:2402.11338
3
citations

FedBAT: Communication-Efficient Federated Learning via Learnable Binarization

Shiwei Li, Wenchao Xu, Haozhao Wang et al.

ICML 2024arXiv:2408.03215
12
citations

FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees

Jiahao Liu, Yipeng Zhou, Di Wu et al.

ICML 2024

Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

Daniel Dodd, Louis Sharrock, Chris Nemeth

ICML 2024spotlightarXiv:2406.02296
1
citations