Imagen de Portada

The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xie, YuQing, Daigavane, Ameya, Kotak, Mit, Smidt, Tess
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
por: Xie, YuQing, et al.
Publicado: (2026)

A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models
por: Xie, YuQing, et al.
Publicado: (2025)

Equivariant Symmetry Breaking Sets
por: Xie, YuQing, et al.
Publicado: (2024)

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation
por: Daigavane, Ameya, et al.
Publicado: (2023)

Training a Foundation Model for Materials on a Budget
por: Koker, Teddy, et al.
Publicado: (2025)

Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational Alignment
por: Daigavane, Ameya, et al.
Publicado: (2025)

PFT: Phonon Fine-tuning for Machine Learned Interatomic Potentials
por: Koker, Teddy, et al.
Publicado: (2026)

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
por: Liao, Yi-Lun, et al.
Publicado: (2026)

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
por: Liao, Yi-Lun, et al.
Publicado: (2023)

Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields
por: Liao, Yi-Lun, et al.
Publicado: (2024)

Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
por: Wang, Rui, et al.
Publicado: (2023)

EquiJump: Protein Dynamics Simulation via SO(3)-Equivariant Stochastic Interpolants
por: Costa, Allan dos Santos, et al.
Publicado: (2024)

Every Bit Counts: A Theoretical Study of Precision-Expressivity Tradeoffs in Quantized Transformers
por: Chakrabarti, Sayak, et al.
Publicado: (2026)

Joint Tensor-Train Parameterization for Efficient and Expressive Low-Rank Adaptation
por: Qi, Jun, et al.
Publicado: (2025)

Expressive Reward Synthesis with the Runtime Monitoring Language
por: Donnelly, Daniel, et al.
Publicado: (2025)

Relaxed Equivariant Graph Neural Networks
por: Hofgard, Elyssa, et al.
Publicado: (2024)

Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
por: Spieler, Aaron, et al.
Publicado: (2026)

Search-contempt: a hybrid MCTS algorithm for training AlphaZero-like engines with better computational efficiency
por: Joshi, Ameya
Publicado: (2025)

Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
por: Chen, Yuzhu, et al.
Publicado: (2025)

Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning
por: Lee, Joohyung, et al.
Publicado: (2023)

Neural Control and Certificate Repair via Runtime Monitoring
por: Yu, Emily, et al.
Publicado: (2024)

Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body Coupling
por: Jin, Dian, et al.
Publicado: (2026)

On the Stability of Expressive Positional Encodings for Graphs
por: Huang, Yinan, et al.
Publicado: (2023)

Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
por: Li, Zimu, et al.
Publicado: (2022)

Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery
por: Hoyos, Paulina, et al.
Publicado: (2026)

Mixture of Latent Experts Using Tensor Products
por: Su, Zhan, et al.
Publicado: (2024)

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS
por: De Schouwer, Jonas, et al.
Publicado: (2026)

Quantifying Empirical Compute-Supervision Tradeoffs in RLVR
por: Mitsuhashi, Ryo, et al.
Publicado: (2026)

Scalable Policy-Based RL Algorithms for POMDPs
por: Anjarlekar, Ameya, et al.
Publicado: (2025)

Attention-based Iterative Decomposition for Tensor Product Representation
por: Park, Taewon, et al.
Publicado: (2024)

CombAlign: Enhancing Model Expressiveness in Unsupervised Graph Alignment
por: Chen, Songyang, et al.
Publicado: (2024)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
por: Li, Haoran, et al.
Publicado: (2025)

Modeling Multi-Objective Tradeoffs with Monotonic Utility Functions
por: Chen, Edward, et al.
Publicado: (2024)

RAP: Runtime Adaptive Pruning for LLM Inference
por: Liu, Huanrong, et al.
Publicado: (2025)

Level Generation with Constrained Expressive Range
por: Bazzaz, Mahsa, et al.
Publicado: (2025)

On the Expressive Power of GNNs for Boolean Satisfiability
por: Peltonen, Saku, et al.
Publicado: (2026)

Understanding Expressivity of GNN in Rule Learning
por: Qiu, Haiquan, et al.
Publicado: (2023)

On the Expressive Power of Graph Neural Networks
por: Nalwade, Ashwin, et al.
Publicado: (2024)

An Empirical Study of Realized GNN Expressiveness
por: Wang, Yanbo, et al.
Publicado: (2023)

On the Expressive Power of Sparse Geometric MPNNs
por: Sverdlov, Yonatan, et al.
Publicado: (2024)