Cover Image

Prediction Is Not Physics: Learning and Evaluating Conserved Quantities in Neural Simulators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bukowski, Andrew, Kothari, Aditya, Shi, Simba, Rao, Ishir
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Fisher-Orthogonal Projected Natural Gradient Descent for Continual Learning
by: Garg, Ishir, et al.
Published: (2026)

Modeling and Optimization of Epidemiological Control Policies Through Reinforcement Learning
by: Rao, Ishir
Published: (2024)

MemFail: Stress-Testing Failure Modes of LLM Memory Systems
by: Garg, Ishir, et al.
Published: (2026)

Simulation-Free Differential Dynamics through Neural Conservation Laws
by: Hua, Mengjian, et al.
Published: (2025)

Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?
by: Sajith, Aryan, et al.
Published: (2024)

Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction
by: Mi, Yuan, et al.
Published: (2024)

Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning
by: Chen, Haohui, et al.
Published: (2025)

Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies
by: Liu, Qi, et al.
Published: (2024)

A Robust Clustered Federated Learning Approach for Non-IID Data with Quantity Skew
by: Ali, Michael Ben, et al.
Published: (2025)

Unified Optimization of Source Weights and Transfer Quantities in Multi-Source Transfer Learning: An Asymptotic Framework
by: Zhang, Qingyue, et al.
Published: (2026)

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
by: Zhang, Qingyue, et al.
Published: (2025)

From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning
by: Ali, Adnan, et al.
Published: (2024)

Conservative Prediction via Data-Driven Confidence Minimization
by: Choi, Caroline, et al.
Published: (2023)

Weakly Supervised Learning on Large Graphs
by: Prakash, Aditya
Published: (2025)

Transfer learning in Scalable Graph Neural Network for Improved Physical Simulation
by: Shen, Siqi, et al.
Published: (2025)

COSBO: Conservative Offline Simulation-Based Policy Optimization
by: Kargar, Eshagh, et al.
Published: (2024)

Meta-Learning and Knowledge Discovery based Physics-Informed Neural Network for Remaining Useful Life Prediction
by: Wang, Yu, et al.
Published: (2025)

Local Data Quantity-Aware Weighted Averaging for Federated Learning with Dishonest Clients
by: Wu, Leming, et al.
Published: (2025)

Mildly Conservative Q-Learning for Offline Reinforcement Learning
by: Lyu, Jiafei, et al.
Published: (2022)

Automated Discovery of Conservation Laws via Hybrid Neural ODE-Transformers
by: Doshi, Vivan
Published: (2025)

Latent-Predictive Empowerment: Measuring Empowerment without a Simulator
by: Levy, Andrew, et al.
Published: (2024)

COMPOL: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations
by: Sun, Yifei, et al.
Published: (2025)

Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation
by: Xu, Jinda, et al.
Published: (2025)

DNAD: Differentiable Neural Architecture Distillation
by: Rao, Xuan, et al.
Published: (2025)

Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management
by: Zhang, Runze, et al.
Published: (2025)

Conservative Distributional Reinforcement Learning with Safety Constraints
by: Zhang, Hengrui, et al.
Published: (2022)

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
by: Rao, Xuan, et al.
Published: (2022)

Momentum-Conserving Graph Neural Networks for Deformable Objects
by: Wang, Jiahong, et al.
Published: (2026)

Physics-Informed Neural Network Surrogate Models for River Stage Prediction
by: Zoch, Maximilian, et al.
Published: (2025)

Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
by: Han, Chao, et al.
Published: (2026)

Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations
by: Kvinge, Henry, et al.
Published: (2026)

Physics-Informed Neural Networks for Vessel Trajectory Prediction: Learning Time-Discretized Kinematic Dynamics via Finite Differences
by: Alam, Md Mahbub, et al.
Published: (2025)

Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
by: Venkatesh, Vinay, et al.
Published: (2025)

Predicting Weekly Fishing Concentration Zones through Deep Learning Integration of Heterogeneous Environmental Spatial Datasets
by: Rele, Chaitanya, et al.
Published: (2025)

Quality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information
by: Chen, Fei, et al.
Published: (2025)

Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen
by: Li, Zihao, et al.
Published: (2025)

Contrastive Dual-Interaction Graph Neural Network for Molecular Property Prediction
by: Zhao, Zexing, et al.
Published: (2024)

Learning Physics Informed Neural ODEs With Partial Measurements
by: Ghanem, Paul, et al.
Published: (2024)

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs
by: Banerjee, Debangshu, et al.
Published: (2023)

Temporal-Aware Evaluation and Learning for Temporal Graph Neural Networks
by: Su, Junwei, et al.
Published: (2024)