8 papers
Symplectic Neural Networks for Learning Non-Separable Hamiltonians
Harsh Choudhary, Vyacheslav Kungurtsev, Chandan Gupta +2
Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample efficiency. Identifying the…
Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space
Yue Cao, Jianyang Gu, Vyacheslav Kungurtsev +4
Dataset distillation (DD) has proven to reduce training cost while preserving accuracy. While promising, the factors that make one distilled dataset more effective than another rem…
CONCORD: Concept-Informed Diffusion for Dataset Distillation
Jianyang Gu, Haonan Wang, Ruoxi Jia +4
Dataset distillation (DD) has witnessed significant progress in creating small datasets that encapsulate rich information from large original ones. Particularly, methods based on g…
Truss topology design under harmonic loads: Peak power minimization with semidefinite programming
Shenyuan Ma, Jakub Marecek, Vyacheslav Kungurtsev +1
Designing lightweight yet stiff structures that can withstand vibrations is a crucial task in structural optimization. Here, we present a novel framework for truss topology optimiz…
Group Distributionally Robust Dataset Distillation with Risk Minimization
Saeed Vahidian, Mingyu Wang, Jianyang Gu +3
Dataset distillation (DD) has emerged as a widely adopted technique for crafting a synthetic dataset that captures the essential information of a training dataset, facilitating the…
Dataset Distillation from First Principles: Integrating Core Information Extraction and Purposeful Learning
Vyacheslav Kungurtsev, Yuanfang Peng, Jianyang Gu +4
Dataset distillation (DD) is an increasingly important technique that focuses on constructing a synthetic dataset capable of capturing the core information in training data to achi…