paper-with-me

홈 › Papers

Tuning Learning Rates with the Cumulative-Learning Constant

2025-04-30 · Nathan Faraj

This paper introduces a novel method for optimizing learning rates in machine learning. A previously unrecognized proportionality between learning rates and dataset sizes is discovered, providing valuable insights into how dataset scale influences training dynamics. Additionally, a cumulative learning constant is identified, offering a framework for designing and optimizing advanced learning rate schedules. These findings have the potential to enhance training efficiency and performance across a wide range of machine learning applications.

📄 PDF Abstract BibTeX arXiv:2505.13457

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Agile Online Model Selection: Resolving Adaptation Lag via Safeguarded Large Learning Rates

2026-05-26 · Kei Takemura, Ryuta Matsuno, Keita Sakuma arxiv

Maintaining predictive accuracy in non-stationary environments requires online model selection to adapt autonomously to unknown distribution shifts. However, existing tuning-free algorithms face a fundamental trade-off b…

From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization

2026-06-01 · Moses Charikar, Chirag Pabbaraju, Ambuj Tewari arxiv

Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal $O(\sqrt{T})$ regret for general convex losses and $O(\log T)$ regret under …

Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates

2025-02-11 · Jincheng Mei, Bo Dai, Alekh Agarwal, Sharan Vaswani 외

We provide a new understanding of the stochastic gradient bandit algorithm by showing that it converges to a globally optimal policy almost surely using \emph{any} constant learning rate. This result demonstrates that th…

A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem

2020-04-08 · Udari Madhushani, Naomi Ehrich Leonard

We define and analyze a multi-agent multi-armed bandit problem in which decision-making agents can observe the choices and rewards of their neighbors under a linear observation cost. Neighbors are defined by a network gr…

Decision Making

Near-Constant Strong Violation and Last-Iterate Convergence for Online CMDPs via Decaying Safety Margins

2026-02-11 · Qian Zuo, Zhiyong Wang, Fengxiang He arxiv

We study safe online reinforcement learning in Constrained Markov Decision Processes (CMDPs) under strong regret and violation metrics, which forbid error cancellation over time. Existing primal-dual methods that achieve…

Reinforcement Learning