SearcharxivSearch

arXiv subjects

Yanchao Shi

Publications and source records attributed to Yanchao Shi.

6 recordsLinked to original sources

Architecture--Optimization Co-Design for Physics-Informed Neural Networks via Layer-wise Coordinate Adaptation and Gradient Conflict Resolution

Physics-informed neural networks (PINNs) can be limited by coordinate representations and conflicting gradients from heterogeneous physical constraints. We propose Architecture--Conflict-Resolved PINN (ACR-PINN), combining Layer-wise Dynamic Adaptation (LDA) and Gradient-Conflict-Resolved PINN (GCR-PINN). LDA constructs layer-specific coordinate features and fuses two encoding branches through input-conditioned, feature-wise gates. GCR-PINN treats PDE, initial-condition, and boundary-condition losses as separate tasks and conditionally projects negatively aligned gradients before aggregation, without changing the physical loss formulation. Across seven benchmark problems, ACR-PINN achieves the lowest observed mean across all metrics among four core architecture--optimizer combinations, reducing mean relative $L_2$ error by approximately 56--97\% relative to Std-PINN and improving on the better single-component variant. Capacity-controlled comparisons and gate interventions indicate that these gains reflect the learned coordinate-fusion pathway rather than parameter count alone. Gradient diagnostics suggest that LDA can improve task-gradient compatibility and reduce the correction required by GCR-PINN, with effects depending on the problem and update rule. Comparisons with representative PINN baselines and tests over sampling and temporal-horizon changes support the observed accuracy gains within the studied settings, while equal-time experiments reveal an accuracy--cost trade-off from the richer LDA representation.

cs.LG

DeSyR: A Decoupled Symbolic Recovery Framework with PINN-Guided Structure Search and Physics-Informed Coefficient Refinement

Recovering compact explicit solutions from neural approximations is challenging when imperfect teacher data guide symbolic topology search and coefficient estimation. We present DeSyR, a decoupled symbolic recovery framework for differential equations. A physics-informed neural network guides repeated searches to construct candidate topologies with provisional constants. Once a topology is fixed, its coefficients are refined solely from the governing equation and prescribed constraints, followed by gated selection and verification. For linear fixed-topology parameterizations, we characterize teacher-error inheritance and show that finite-weight mixed data--physics fitting retains an $O(β^{-1})$ teacher-dependent contribution when the teacher error projects onto the model space. Under well-posedness, representability, zero-residual attainment, and discrete determinacy, physics-only refinement conditionally recovers exact coefficients; for nonlinear parameterizations, the corresponding guarantees are local. DeSyR is evaluated on 15 differential-equation problems across 18 configurations covering high-order, space--time, multidimensional, nonlinear, and coupled systems. A candidate-level audit yields a 99.23% convergence rate among free-parameter refits, while every selected refinement involving free coefficients converges. Configuration-level median refined relative $L_2$ errors are $2.31\times10^{-14}$ or lower. In same-topology comparisons, refinement reduces error by eight to fourteen orders of magnitude. These results show that an approximate neural teacher can guide topology discovery without imposing its error scale on final recovered coefficients, provided a target-capable topology is retained and physics-only refinement converges.

cs.LG

Improved physics-informed neural network in mitigating gradient related failures

Physics-informed neural networks (PINNs) integrate fundamental physical principles with advanced data-driven techniques, driving significant advancements in scientific computing. However, PINNs face persistent challenges with stiffness in gradient flow, which limits their predictive capabilities. This paper presents an improved PINN (I-PINN) to mitigate gradient-related failures. The core of I-PINN is to combine the respective strengths of neural networks with an improved architecture and adaptive weights containingupper bounds. The capability to enhance accuracy by at least one order of magnitude and accelerate convergence, without introducing extra computational complexity relative to the baseline model, is achieved by I-PINN. Numerical experiments with a variety of benchmarks illustrate the improved accuracy and generalization of I-PINN. The supporting data and code are accessible at https://github.com/PanChengN/I-PINN.git, enabling broader research engagement.

cs.LG

Few-femtosecond Electron Beam with THz-frequency Wakefield-driven Compression

We propose and demonstrate a novel method to produce few-femtosecond electron beam with relatively low timing jitter. In this method a relativistic electron beam is compressed from about 150 fs (rms) to about 7 fs (rms, upper limit) with the wakefield at THz frequency produced by a leading drive beam in a dielectric tube. By imprinting the energy chirp in a passive way, we demonstrate through laser-driven THz streaking technique that no additional timing jitter with respect to an external laser is introduced in this bunch compression process, a prominent advantage over the conventional method using radio-frequency bunchers. We expect that this passive bunching technique may enable new opportunities in many ultrashort-beam based advanced applications such as ultrafast electron diffraction and plasma wakefield acceleration.

physics.acc-ph

Terahertz streaking of few-femtosecond relativistic electron beams

Streaking of photoelectrons with optical lasers has been widely used for temporal characterization of attosecond extreme ultraviolet pulses. Recently, this technique has been adapted to characterize femtosecond x-ray pulses in free-electron lasers with the streaking imprinted by farinfrared and Terahertz (THz) pulses. Here, we report successful implementation of THz streaking for time-stamping of an ultrashort relativistic electron beam of which the energy is several orders of magnitude higher than photoelectrons. Such ability is especially important for MeV ultrafast electron diffraction (UED) applications where electron beams with a few femtosecond pulse width may be obtained with longitudinal compression while the arrival time may fluctuate at a much larger time scale. Using this laser-driven THz streaking technique, the arrival time of an ultrashort electron beam with 6 fs (rms) pulse width has been determined with 1.5 fs (rms) accuracy. Furthermore, we have proposed and demonstrated a non-invasive method for correction of the timing jitter with femtosecond accuracy through measurement of the compressed beam energy, which may allow one to advance UED towards sub-10 fs frontier far beyond the ~100 fs (rms) jitter.

physics.acc-ph

Elongation of energy exchange between femtosecond laser pulses via plasma formation in air

We experimentally demonstrate energy exchange between a delay-tuned femtosecond beam and two delay-fixed ones as they spatiotemporally overlapped and experienced filamentation in air. The energy exchange process in the relative time delay is dramatically elongated up to 40 ps in the presence of plasma grating, indicating that filamentary beams coupling may be an effective method for filament control.

physics.optics