6 papers
Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
Yanna Ding, Songtao Lu, Yingdong Lu +2
Transformer architectures can solve unseen tasks based on input-output pairs in a given prompt due to in-context learning (ICL). Existing theoretical studies on ICL have mainly foc…
Gradient Flow Matching for Learning Update Dynamics in Neural Network Training
Xiao Shou, Yanna Ding, Jianxi Gao
Training deep neural networks remains computationally intensive due to the itera2 tive nature of gradient-based optimization. We propose Gradient Flow Matching (GFM), a continuous-…
Efficient parameter inference in networked dynamical systems via steady states: A surrogate objective function approach integrating mean-field and nonlinear least squares
Yanna Ding, Malik Magdon-Ismail, Jianxi Gao
In networked dynamical systems, inferring governing parameters is crucial for predicting nodal dynamics, such as gene expression levels, species abundance, or population density. W…
Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection
Mingyu Derek Ma, Yanna Ding, Zijie Huang +3
Generative Language Models rely on autoregressive decoding to produce the output sequence token by token. Many tasks such as preference optimization, require the model to produce t…
Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation
Yanna Ding, Zijie Huang, Xiao Shou +3
Learning curve extrapolation predicts neural network performance from early training epochs and has been applied to accelerate AutoML, facilitating hyperparameter tuning and neural…
Predicting Time Series of Networked Dynamical Systems without Knowing Topology
Yanna Ding, Zijie Huang, Malik Magdon-Ismail +1
Many real-world complex systems, such as epidemic spreading networks and ecosystems, can be modeled as networked dynamical systems that produce multivariate time series. Learning t…