arXiv subjects

Yuanjun Dai

Publications and source records attributed to Yuanjun Dai.

6 recordsLinked to original sources

arXiv2026

A Compensated Koopman Neural Operator with Selective State-Space Dynamics for Unsteady Flows

Stable prediction of unsteady flows requires accurate multiscale spatial representation and robust temporal propagation. We introduce the Compensated Koopman U-shaped Neural Operator (CoKo-UNO), which combines a U-shaped spectral backbone with Koopman-dominated latent propagation. Finite-dimensional Koopman truncation produces a state-dependent residual that is repeatedly reinjected during autoregressive rollout. CoKo-UNO models this residual with a selective state-space model (SSM), a principled input-dependent compensation mechanism, together with resolution-adaptive compensatory skip connections and an overlapping-warmup rollout strategy. \NEW{Across four benchmark problems, CoKo-UNO achieves the lowest mean rollout error among all compared methods. Its largest gain is a $76.76\%$ reduction relative to the strongest baseline, while requiring about $41.40\%$ of RNO's training time.} These results show that explicit residual compensation improves stable autoregressive prediction of unsteady flows.

physics.flu-dyn↗

arXiv2026

Data-driven Symbolic Closure for Turbulence Modeling in the Lattice Boltzmann Framework

Turbulence modeling within the Lattice Boltzmann Method (LBM) framework has long relied on traditional algebraic sub-grid scale (SGS) models, which often suffer from over-dissipation and lack of spatial selectivity near solid boundaries. In this work, we utilize Physical Symbolic Optimization (Phi-SO) to discover explicit analytical closures from high-fidelity DNS datasets of Taylor-Green Vortex (TGV) and Lid-Driven Cavity (LDC) flows. Central to our methodology is the integration of virtual dimensional analysis and non-linear tensor invariants, a strategy that enforces physical scaling laws directly within the symbolic search process. The resulting model exhibits a highly non-linear dependency on both strain-rate and rotation-rate invariants. Numerical validations confirm that this symbolic closure outperforms the standard Smagorinsky approach in capturing kinetic energy dissipation rate peaks and resolving delicate secondary corner vortices. Furthermore, the model exhibits robust zero-shot generalization to wall-bounded turbulent channel flow (Re_tau = 180) without the aid of any supplemental wall-damping corrections. This work highlights the potential of symbolic regression to uncover robust, interpretable physical laws for the next generation of intelligent computational fluid dynamics solvers.

physics.flu-dyn↗

arXiv2025

DYNAMIX: RL-based Adaptive Batch Size Optimization in Distributed Machine Learning Systems

Existing batch size selection approaches in distributed machine learning rely on static allocation or simplistic heuristics that fail to adapt to heterogeneous, dynamic computing environments. We present DYNAMIX, a reinforcement learning framework that formulates batch size optimization as a sequential decision-making problem using Proximal Policy Optimization (PPO). Our approach employs a multi-dimensional state representation encompassing network-level metrics, system-level resource utilization, and training statistical efficiency indicators to enable informed decision-making across diverse computational resources. Our approach eliminates the need for explicit system modeling while integrating seamlessly with existing distributed training frameworks. Through evaluations across diverse workloads, hardware configurations, and network conditions, DYNAMIX achieves up to 6.3% improvement in the final model accuracy and 46% reduction in the total training time. Our scalability experiments demonstrate that DYNAMIX maintains the best performance as cluster size increases to 32 nodes, while policy transfer experiments show that learned policies generalize effectively across related model architectures.

cs.LG↗

arXiv2025

eHashPipe: Lightweight Top-K and Per-PID Resource Monitoring with eBPF

System-level resource monitoring with both precision and efficiency is a continuous challenge. We introduce eHashPipe, a lightweight, real-time resource observability system utilizing eBPF and the HashPipe sketching algorithm. eHashPipe supports two tracking modes: Top-k monitoring to identify the most resource-demanding processes and specific PID tracking to detail the behavior of selected processes. We implement two in-kernel eBPF pipelines for on-CPU time and memory usage. Unlike traditional userspace polling tools, eHashPipe operates in the kernel to reduce latency and context-switch overhead while keeping the runtime footprint small. During our experiments, eHashPipe attains 100 percent Top-k precision for CPU and memory at k = 1, 5, and 10, 95.0/90.0 percent at k = 20, and 93.3/83.3 percent at k = 30 compared to the ground truth. It exposes short-lived bursts with about 14 times finer temporal resolution than top while imposing very low overhead. These results show that eHashPipe delivers accurate, responsive insight with minimal impact, making it well suited for latency-sensitive cloud and edge environments.

cs.PF↗

arXiv2025

PSketch: A Priority-Aware Sketch Architecture for Real-Time Flow Monitoring via eBPF

Sketch-based monitoring in SDN often suffers from tightly coupled pipeline and memory constraints, limiting algorithmic flexibility and reducing accuracy. We propose PSketch, the first in-kernel priority-aware sketching framework implemented with eBPF. It ensures lossless tracking of high-priority flows via a hash-based table and approximates top-k elephant flows using a sketch pipe. PSketch supports both TCP and UDP and enables in-kernel retransmission tracking with minimal overhead. Unlike SDN-based approaches, it runs on commodity Linux systems, removing hardware dependencies. We perform evaluation on 10 Gbps CAIDA traces. Results show that PSketch achieves 96.0% top-k detection accuracy, 96.4% retransmission recall, and only 0.7% throughput degradation.

cs.ET↗

arXiv2022

FourNetFlows: An efficient model for steady airfoil flows prediction

FourNetFlows, the abbreviation of Fourier Neural Network for Airfoil Flows, is an efficient model that provides quick and accurate predictions of steady airfoil flows. We choose the Fourier Neural Operator (FNO) as the backbone architecture and utilize OpenFOAM to generate numerical solutions of airfoil flows for training. Our results indicate that FourNetFlows matches the accuracy of the Semi-Implicit Method for Pressure Linked Equations (SIMPLE) integrated with the Spalart-Allmaras turbulence model, one of the numerical algorithms. FourNetFlows is also used to predict flows around an oval whose shape is definitely different from samples in the training set. We note that both qualitative and quantitative results are consistent with the numerical results. Meanwhile, FourNetFlows solves thousands of solutions in seconds, orders of magnitude faster than the classical numerical method. Surprisingly, FourNetFlows achieves model flows with zero-shot super-resolution when it is trained under a lower resolution. And the inferring time is almost constant when the resolution of solutions is increasing.

physics.flu-dyn↗