8 citations · 13 across the 5 of their papers we have counts for
5 papers
Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
Junbin Qiu, Zhaowei Hong, Renzhe Xu +1
Accurate Zeroth-Order (ZO) Hessian estimation is a cornerstone of derivative-free methods, essential for tasks such as bilevel optimization, Bayesian inference, and uncertainty qua…
Zeroth-Order Optimization is Secretly Single-Step Policy Optimization
Junbin Qiu, Zhengpeng Xie, Xiangda Yan +2
Zeroth-Order Optimization (ZOO) provides powerful tools for optimizing functions where explicit gradients are unavailable or expensive to compute. However, the underlying mechanism…
An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos
Junbin Qiu, Haiping Huang
Understanding neural dynamics is a central topic in machine learning, non-linear physics and neuroscience. However, the dynamics is non-linear, stochastic and particularly non-grad…
Meta predictive learning model of languages in neural circuits
Chan Li, Junbin Qiu, Haiping Huang
Large language models based on self-attention mechanisms have achieved astonishing performances not only in natural language itself, but also in a variety of tasks of different nat…
Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems
Yang Zhao, Junbin Qiu, Mingshan Xie +1
Binary perceptron is a fundamental model of supervised learning for the non-convex optimization, which is a root of the popular deep learning. Binary perceptron is able to achieve…