:: Library Catalog

Image de couverture de livre

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Zhanpeng, Yang, Yongyi, Sugiyama, Mahito, Yan, Junchi
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	https://arxiv.org/abs/2505.13900
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Cone Effect in the Learning Dynamics
par: Zhou, Zhanpeng, et autres
Publié: (2025)

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
par: Zhang, Tongcheng, et autres
Publié: (2026)

Linear Mode Connectivity in Differentiable Tree Ensembles
par: Kanoh, Ryuichi, et autres
Publié: (2024)

A Complete Decomposition of KL Error using Refined Information and Mode Interaction Selection
par: Enouen, James, et autres
Publié: (2024)

When Graph Language Models Go Beyond Memorization
par: Yamada, Masatsugu, et autres
Publié: (2026)

Pseudo-Nonlinear Data Augmentation: A Constrained Energy Minimization Viewpoint
par: Hu, Pingbang, et autres
Publié: (2024)

StiefelGen: A Simple, Model Agnostic Approach for Time Series Data Augmentation over Riemannian Manifolds
par: Cheema, Prasad, et autres
Publié: (2024)

Dual Riemannian Newton Method on Statistical Manifolds
par: Zhou, Derun, et autres
Publié: (2025)

How Graph Neural Networks Learn: Lessons from Training Dynamics
par: Yang, Chenxiao, et autres
Publié: (2023)

Bringing Structure to Naturalness: On the Naturalness of ASTs
par: Pârţachi, Profir-Petru, et autres
Publié: (2025)

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
par: Zhou, Zhanpeng, et autres
Publié: (2024)

On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm
par: Zhou, Zhanpeng, et autres
Publié: (2024)

An Equivariance Toolbox for Learning Dynamics
par: Yang, Yongyi, et autres
Publié: (2025)

Quadratic polarity and polar Fenchel-Young divergences from the canonical Legendre polarity
par: Nielsen, Frank, et autres
Publié: (2026)

On the Role of Label Noise in the Feature Learning Process
par: Han, Andi, et autres
Publié: (2025)

Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks
par: Wang, Runzhong, et autres
Publié: (2024)

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
par: Wang, Jinbo, et autres
Publié: (2025)

HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
par: Yang, Yongyi, et autres
Publié: (2024)

Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach
par: Ai, Xing, et autres
Publié: (2022)

EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
par: Chen, Chao, et autres
Publié: (2023)

Implicit vs Unfolded Graph Neural Networks
par: Yang, Yongyi, et autres
Publié: (2021)

Same Graph, Different Likelihoods: Calibration of Autoregressive Graph Generators via Permutation-Equivalent Encodings
par: Fredsgaard, Laurits, et autres
Publié: (2026)

Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation
par: Yan, Hao, et autres
Publié: (2025)

NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
par: Qin, Xiaohan, et autres
Publié: (2025)

Transformers from Diffusion: A Unified Framework for Neural Message Passing
par: Wu, Qitian, et autres
Publié: (2024)

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
par: Pang, Tianyu, et autres
Publié: (2026)

Provable Low-Frequency Bias of In-Context Learning of Representations
par: Yang, Yongyi, et autres
Publié: (2025)

Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
par: Wang, Ziqiao, et autres
Publié: (2022)

Learning Divergence Fields for Shift-Robust Graph Representations
par: Wu, Qitian, et autres
Publié: (2024)

Swing-by Dynamics in Concept Learning and Compositional Generalization
par: Yang, Yongyi, et autres
Publié: (2024)

Topological Invariance and Breakdown in Learning
par: Yang, Yongyi, et autres
Publié: (2025)

Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics
par: Zhong, Ruizhe, et autres
Publié: (2026)

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
par: Li, Bingrui, et autres
Publié: (2024)

A Model Zoo on Phase Transitions in Neural Networks
par: Schürholt, Konstantin, et autres
Publié: (2025)

Molecule Generation for Drug Design: a Graph Learning Perspective
par: Yang, Nianzu, et autres
Publié: (2022)

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning
par: Huang, Zheng, et autres
Publié: (2024)

mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations
par: Yang, Yongyi, et autres
Publié: (2026)

Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability
par: Zhang, Yu-Jie, et autres
Publié: (2025)

Trustworthy Federated Learning via Blockchain
par: Yang, Zhanpeng, et autres
Publié: (2022)

KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches
par: Feng, Mingquan, et autres
Publié: (2025)