Remove Symmetries to Control Model Expressivity and Improve Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | Ziyin, Liu, Xu, Yizhou, Chuang, Isaac |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Parameter Symmetry Potentially Unifies Deep Learning Theory
by: Ziyin, Liu, et al.
Published: (2025)
by: Ziyin, Liu, et al.
Published: (2025)
Three Mechanisms of Feature Learning in a Linear Network
by: Xu, Yizhou, et al.
Published: (2024)
by: Xu, Yizhou, et al.
Published: (2024)
Thermodynamic Irreversibility of Training Algorithms
by: Ziyin, Liu, et al.
Published: (2026)
by: Ziyin, Liu, et al.
Published: (2026)
Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
by: Xu, Yizhou, et al.
Published: (2026)
by: Xu, Yizhou, et al.
Published: (2026)
Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
by: Ziyin, Liu, et al.
Published: (2025)
by: Ziyin, Liu, et al.
Published: (2025)
Fast Inference of Removal-Based Node Influence
by: Li, Weikai, et al.
Published: (2024)
by: Li, Weikai, et al.
Published: (2024)
A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
by: Xiao, Tim Z., et al.
Published: (2023)
by: Xiao, Tim Z., et al.
Published: (2023)
Noise Balance and Stationary Distribution of Stochastic Gradient Descent
by: Ziyin, Liu, et al.
Published: (2023)
by: Ziyin, Liu, et al.
Published: (2023)
From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection
by: Wang, Luzhi, et al.
Published: (2026)
by: Wang, Luzhi, et al.
Published: (2026)
The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models
by: Zhao, Zhiyu, et al.
Published: (2026)
by: Zhao, Zhiyu, et al.
Published: (2026)
CombAlign: Enhancing Model Expressiveness in Unsupervised Graph Alignment
by: Chen, Songyang, et al.
Published: (2024)
by: Chen, Songyang, et al.
Published: (2024)
Compositional Generalization via Forced Rendering of Disentangled Latents
by: Liang, Qiyao, et al.
Published: (2025)
by: Liang, Qiyao, et al.
Published: (2025)
Are Expressive Models Truly Necessary for Offline RL?
by: Wang, Guan, et al.
Published: (2024)
by: Wang, Guan, et al.
Published: (2024)
Expanding Expressivity in Transformer Models with MöbiusAttention
by: Halacheva, Anna-Maria, et al.
Published: (2024)
by: Halacheva, Anna-Maria, et al.
Published: (2024)
How Expressive are Knowledge Graph Foundation Models?
by: Huang, Xingyue, et al.
Published: (2025)
by: Huang, Xingyue, et al.
Published: (2025)
ExBody2: Advanced Expressive Humanoid Whole-Body Control
by: Ji, Mazeyu, et al.
Published: (2024)
by: Ji, Mazeyu, et al.
Published: (2024)
Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency
by: Chen, Rongqin, et al.
Published: (2025)
by: Chen, Rongqin, et al.
Published: (2025)
Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
by: Niu, Haoyi, et al.
Published: (2023)
by: Niu, Haoyi, et al.
Published: (2023)
Implicit Language Models are RNNs: Balancing Parallelization and Expressivity
by: Schöne, Mark, et al.
Published: (2025)
by: Schöne, Mark, et al.
Published: (2025)
Understanding the Emergence of Multimodal Representation Alignment
by: Tjandrasuwita, Megan, et al.
Published: (2025)
by: Tjandrasuwita, Megan, et al.
Published: (2025)
The Role of Symmetry in Optimizing Overparameterized Networks
by: Sareen, Kusha, et al.
Published: (2026)
by: Sareen, Kusha, et al.
Published: (2026)
OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models
by: Zhang, Jianzhang, et al.
Published: (2025)
by: Zhang, Jianzhang, et al.
Published: (2025)
Proof of a perfect platonic representation hypothesis
by: Ziyin, Liu, et al.
Published: (2025)
by: Ziyin, Liu, et al.
Published: (2025)
Building Expressive and Tractable Probabilistic Generative Models: A Review
by: Sidheekh, Sahil, et al.
Published: (2024)
by: Sidheekh, Sahil, et al.
Published: (2024)
When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics
by: Zhang, Yizhou
Published: (2025)
by: Zhang, Yizhou
Published: (2025)
Controlling Grokking with Nonlinearity and Data Symmetry
by: Salah, Ahmed, et al.
Published: (2024)
by: Salah, Ahmed, et al.
Published: (2024)
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
by: Cao, Defu, et al.
Published: (2024)
by: Cao, Defu, et al.
Published: (2024)
On the Expressive Power of Graph Neural Networks
by: Nalwade, Ashwin, et al.
Published: (2024)
by: Nalwade, Ashwin, et al.
Published: (2024)
On the Expressive Power of Sparse Geometric MPNNs
by: Sverdlov, Yonatan, et al.
Published: (2024)
by: Sverdlov, Yonatan, et al.
Published: (2024)
Level Generation with Constrained Expressive Range
by: Bazzaz, Mahsa, et al.
Published: (2025)
by: Bazzaz, Mahsa, et al.
Published: (2025)
On the Expressive Power of GNNs for Boolean Satisfiability
by: Peltonen, Saku, et al.
Published: (2026)
by: Peltonen, Saku, et al.
Published: (2026)
Understanding Expressivity of GNN in Rule Learning
by: Qiu, Haiquan, et al.
Published: (2023)
by: Qiu, Haiquan, et al.
Published: (2023)
On the Stability of Expressive Positional Encodings for Graphs
by: Huang, Yinan, et al.
Published: (2023)
by: Huang, Yinan, et al.
Published: (2023)
An Empirical Study of Realized GNN Expressiveness
by: Wang, Yanbo, et al.
Published: (2023)
by: Wang, Yanbo, et al.
Published: (2023)
Continual Optimization with Symmetry Teleportation for Multi-Task Learning
by: Zhou, Zhipeng, et al.
Published: (2025)
by: Zhou, Zhipeng, et al.
Published: (2025)
Reasoning Language Model for Personalized Lung Cancer Screening
by: Niu, Chuang, et al.
Published: (2025)
by: Niu, Chuang, et al.
Published: (2025)
On the Expressive Power of Tree-Structured Probabilistic Circuits
by: Yin, Lang, et al.
Published: (2024)
by: Yin, Lang, et al.
Published: (2024)
EXPO: Stable Reinforcement Learning with Expressive Policies
by: Dong, Perry, et al.
Published: (2025)
by: Dong, Perry, et al.
Published: (2025)
Are Expressive Encoders Necessary for Discrete Graph Generation?
by: Revolinsky, Jay, et al.
Published: (2026)
by: Revolinsky, Jay, et al.
Published: (2026)
Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning
by: Xu, Isaac, et al.
Published: (2026)
by: Xu, Isaac, et al.
Published: (2026)
Similar Items
-
Parameter Symmetry Potentially Unifies Deep Learning Theory
by: Ziyin, Liu, et al.
Published: (2025) -
Three Mechanisms of Feature Learning in a Linear Network
by: Xu, Yizhou, et al.
Published: (2024) -
Thermodynamic Irreversibility of Training Algorithms
by: Ziyin, Liu, et al.
Published: (2026) -
Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
by: Xu, Yizhou, et al.
Published: (2026) -
Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
by: Ziyin, Liu, et al.
Published: (2025)