9 papers
Momentum in large-batch training: Polyak enlarges the critical batch size, Nesterov improves data efficiency
Jia-Nan Wang, Zixun Huang, Kairui Li +1
We study when and how momentum improves large-batch training in the one-pass regime, using power-law kernel regression as a tractable setting. We first characterize risk stability…
Variance-Aware Baselines and Adaptive Learning Rates for Reinforcement Learning with Verifiable Rewards
Zixun Huang, Jiayi Sheng, Zeyu Zheng
Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of its baselines and learning-rat…
Functional Scaling Laws in Kernel Regression: Loss Dynamics and Learning Rate Schedules
Binghui Li, Fengling Chen, Zixun Huang +2
Scaling laws have emerged as a unifying lens for understanding and guiding the training of large language models (LLMs). However, existing studies predominantly focus on the final-…
Towards Generalizable Context-aware Anomaly Detection: A Large-scale Benchmark in Cloud Environments
Xinkai Zou, Xuan Jiang, Ruikai Huang +8
Anomaly detection in cloud environments remains both critical and challenging. Existing context-level benchmarks typically focus on either metrics or logs and often lack reliable a…
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
Zi-Xuan Huang, Jia-Wei Chen, Zhi-Peng Zhang +1
Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box mode…
Encoding Urban Ecologies: Automated Building Archetype Generation through Self-Supervised Learning for Energy Modeling
Xinwei Zhuang, Zixun Huang, Wentao Zeng +1
As the global population and urbanization expand, the building sector has emerged as the predominant energy consumer and carbon emission contributor. The need for innovative Urban…