arXiv subjects

Jaeheun Jung

Publications and source records attributed to Jaeheun Jung.

6 recordsLinked to original sources

arXiv2025

Data-Driven Dimensional Synthesis of Diverse Planar Four-bar Function Generation Mechanisms via Direct Parameterization

Dimensional synthesis of planar four-bar mechanisms is a challenging inverse problem in kinematics, requiring the determination of mechanism dimensions from desired motion specifications. We propose a data-driven framework that bypasses traditional equation-solving and optimization by leveraging supervised learning. Our method combines a synthetic dataset, an LSTM-based neural network for handling sequential precision points, and a Mixture of Experts (MoE) architecture tailored to different linkage types. Each expert model is trained on type-specific data and guided by a type-specifying layer, enabling both single-type and multi-type synthesis. A novel simulation metric evaluates prediction quality by comparing desired and generated motions. Experiments show our approach produces accurate, defect-free linkages across various configurations. This enables intuitive and efficient mechanism design, even for non-expert users, and opens new possibilities for scalable and flexible synthesis in kinematic design.

cs.LG↗

arXiv2025

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not enough. Across 14 representative unlearning methods on CIFAR-10 and SVHN, a single linear map fitted on a held-out calibration set, with no access to the forgotten data, reverses the unlearning in seconds and recovers forget-set accuracy to within a few percent of the original model. Recovered features even support pixel-level reconstruction through a generic decoder. We call this diagnostic Feature Mapping Recovery (FM-recovery). The pattern it exposes is uniform: current unlearning methods do not erase information from the representation, they apply an invertible linear distortion that hides it from one particular prediction head. We propose One-Point Contraction (OPC), an unlearning objective that collapses forget-set features to the origin while leaving the retain-set geometry intact. We prove that this contraction is equivalent to driving the predictive distribution to maximum entropy, so the same mechanism delivers behavioral forgetting and representation-level erasure at once. Forgotten queries land in a region the network treats as out-of-distribution, and the gradient signal on those queries collapses along with their features. OPC is the only method in our benchmark that survives FM-recovery, resists relearning and gradient-inversion attacks, and decouples forget from retain features in entangled settings, all without sacrificing retain or test accuracy.

cs.LG↗

arXiv2025

Catalyst: a Novel Regularizer for Structured Pruning with Auxiliary Extension of Parameter Space

Structured pruning aims to reduce the size and computational cost of deep neural networks by removing entire filters or channels. The traditional regularizers such as L1 or Group Lasso and its variants lead to magnitude-biased pruning decisions, such that the filters with small magnitudes are likely to be pruned. Also, they often entail pruning results with almost zero margin around pruning decision boundary, such that tiny perturbation in a filter magnitude can flip the pruning decision. In this paper, we identify the precise algebraic condition under which pruning operations preserve model performance, and use the condition to construct a novel regularizer defined in an extended parameter space via auxiliary catalyst variables. The proposed Catalyst regularization ensures fair pruning chance for each filters with theoretically provable zero bias to their magnitude and robust pruning behavior achieved by wide-margin bifurcation of magnitudes between the preserved and the pruned filters. The theoretical properties naturally lead to real-world effectiveness, as shown by empirical validations of Catalyst Pruning algorithm. Pruning results on various datasets and models are superior to state-of-the-art filter pruning methods, and at the same time confirm the predicted robust and fair pruning characteristics of Catalyst pruning.

cs.LG↗

arXiv2025

IPPRO: Importance-based Pruning with PRojective Offset for Magnitude-indifferent Structural Pruning

Importance-based structured pruning overwhelmingly relies on filter magnitude. This proxy is fundamentally flawed: due to scale invariance, functionally identical filters can receive arbitrarily different importance scores under rescaling. We propose IPPRO (Importance-based Pruning with PROjective Offset), a scale-invariant pruning framework grounded in projective geometry. By embedding filters into real projective space ($\mathbb{RP}^N$), IPPRO resolves the singularity at the origin, placing all filters at an equal angular distance from the zero filter. We define PROscore, which captures functional importance by measuring a filter's angular displacement toward zero under a single gradient step (directional collapse). We further connect PROscore to exact $L_0$ relaxation, proving this one-shot criterion reliably predicts multi-step pruning dynamics. Extensive experiments across CNNs, Vision Transformers, and LLMs (e.g., ResNet, DeiT, LLaMA) demonstrate that IPPRO consistently outperforms existing methods, yielding particularly striking gains under high compression and no-fine-tuning regimes, IPPRO establishes a robust, architecture-agnostic paradigm for neural network compression.

cs.LG↗

arXiv2025

Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition

Shock waves caused by earthquakes can be devastating. Generating realistic earthquake-caused ground motion waveforms help reducing losses in lives and properties, yet generative models for the task tend to generate subpar waveforms. We present High-fidelity Earthquake Groundmotion Generation System (HEGGS) and demonstrate its superior performance using earthquakes from North American, East Asian, and European regions. HEGGS exploits the intrinsic characteristics of earthquake dataset and learns the waveforms using an end-to-end differentiable generator containing conditional latent diffusion model and hi-fidelity waveform construction model. We show the learning efficiency of HEGGS by training it on a single GPU machine and validate its performance using earthquake databases from North America, East Asia, and Europe, using diverse criteria from waveform generation tasks and seismology. Once trained, HEGGS can generate three dimensional E-N-Z seismic waveforms with accurate P/S phase arrivals, envelope correlation, signal-to-noise ratio, GMPE analysis, frequency content analysis, and section plot analysis.

cs.LG↗

arXiv2020

On completely decomposable defining equations of points in general position in $\mathbb{P}^n$

The study of the defining equations of a finite set $Γ\subset \mathbb{P}^n$ in linearly general position has been actively attracted since it plays a significant role in understanding the defining equations of arithmetically Cohen-Macaulay varieties. In \cite{T}, R. Treger proved that $I(Γ)$ is generated by forms of degree $\leq \lceil \frac{|Γ|}{n}\rceil$. Since then, Treger's result have been extended and improved in several papers. The aim of this paper is to reprove and improve the above Treger's result from a new perspective. Our main result in this paper shows that $I(Γ)$ is generated by the union of $I(Γ)_{\leq \lceil \frac{|Γ|}{n}\rceil -1}$ and the set of all completely decomposable forms of degree $\lceil \frac{|Γ|}{n}\rceil$ in $I(Γ)$. In particular, it holds that if $d \leq 2n$ then $I(Γ)$ is generated by quadratic equations of rank $2$. This reproves Saint-Donat's results in \cite{SD1} and \cite{SD2}.

math.AG↗