LEADS: Learning Dynamical Systems that Generalize Across Environments
- URL: http://arxiv.org/abs/2106.04546v1
- Date: Tue, 8 Jun 2021 17:28:19 GMT
- Title: LEADS: Learning Dynamical Systems that Generalize Across Environments
- Authors: Yuan Yin, Ibrahim Ayed, Emmanuel de B\'ezenac, Nicolas Baskiotis,
Patrick Gallinari
- Abstract summary: We propose LEADS, a novel framework that leverages the commonalities and discrepancies among known environments to improve model generalization.
We show that this new setting can exploit knowledge extracted from environment-dependent data and improves generalization for both known and novel environments.
- Score: 12.024388048406587
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: When modeling dynamical systems from real-world data samples, the
distribution of data often changes according to the environment in which they
are captured, and the dynamics of the system itself vary from one environment
to another. Generalizing across environments thus challenges the conventional
frameworks. The classical settings suggest either considering data as i.i.d.
and learning a single model to cover all situations or learning
environment-specific models. Both are sub-optimal: the former disregards the
discrepancies between environments leading to biased solutions, while the
latter does not exploit their potential commonalities and is prone to scarcity
problems. We propose LEADS, a novel framework that leverages the commonalities
and discrepancies among known environments to improve model generalization.
This is achieved with a tailored training formulation aiming at capturing
common dynamics within a shared model while additional terms capture
environment-specific dynamics. We ground our approach in theory, exhibiting a
decrease in sample complexity with our approach and corroborate these results
empirically, instantiating it for linear dynamics. Moreover, we concretize this
framework for neural networks and evaluate it experimentally on representative
families of nonlinear dynamics. We show that this new setting can exploit
knowledge extracted from environment-dependent data and improves generalization
for both known and novel environments.
Related papers
- SPARTAN: A Sparse Transformer Learning Local Causation [63.29645501232935]
Causal structures play a central role in world models that flexibly adapt to changes in the environment.
We present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns local causal structures between entities in a scene.
By applying sparsity regularisation on the attention pattern between object-factored tokens, SPARTAN identifies sparse local causal models that accurately predict future object states.
arXiv Detail & Related papers (2024-11-11T11:42:48Z) - Dynamic Post-Hoc Neural Ensemblers [55.15643209328513]
In this study, we explore employing neural networks as ensemble methods.
Motivated by the risk of learning low-diversity ensembles, we propose regularizing the model by randomly dropping base model predictions.
We demonstrate this approach lower bounds the diversity within the ensemble, reducing overfitting and improving generalization capabilities.
arXiv Detail & Related papers (2024-10-06T15:25:39Z) - Environment-Aware Dynamic Graph Learning for Out-of-Distribution
Generalization [41.58330883016538]
We study the out-of-distribution (OOD) generalization on dynamic graphs from the environment learning perspective.
We propose a Environment-Aware dynamic Graph LEarning (EAGLE) framework for OOD generalization by modeling complex environments and exploiting novel graph-temporalvariant patterns.
To the best of our knowledge, we are the first to study OOD generalization on dynamic graphs from the environment learning perspective.
arXiv Detail & Related papers (2023-11-18T16:31:10Z) - Generalizing Graph ODE for Learning Complex System Dynamics across
Environments [33.63818978256567]
GG-ODE is a machine learning framework for learning continuous multi-agent system dynamics across environments.
Our model learns system dynamics using neural ordinary differential equations (ODE) parameterized by Graph Neural Networks (GNNs)
Experiments over various physical simulations show that our model can accurately predict system dynamics, especially in the long range.
arXiv Detail & Related papers (2023-07-10T00:29:25Z) - SpReME: Sparse Regression for Multi-Environment Dynamic Systems [6.7053978622785415]
We develop a method of sparse regression dubbed SpReME to discover the major dynamics that underlie multiple environments.
We demonstrate that the proposed model captures the correct dynamics from multiple environments over four different dynamic systems with improved prediction performance.
arXiv Detail & Related papers (2023-02-12T15:45:50Z) - Time Will Change Things: An Empirical Study on Dynamic Language
Understanding in Social Media Classification [5.075802830306718]
We empirically study social media NLU in a dynamic setup, where models are trained on the past data and test on the future.
We show that auto-encoding and pseudo-labeling collaboratively show the best robustness in dynamicity.
arXiv Detail & Related papers (2022-10-06T12:18:28Z) - Generalizing to New Physical Systems via Context-Informed Dynamics Model [0.0]
We propose a new framework for context-informed dynamics adaptation (CoDA)
CoDA learns to condition the dynamics model on contextual parameters, specific to each environment.
We show state-ofthe-art generalization results on a set of nonlinear dynamics, representative of a variety of application domains.
arXiv Detail & Related papers (2022-02-01T07:41:10Z) - Learning to Continuously Optimize Wireless Resource in a Dynamic
Environment: A Bilevel Optimization Perspective [52.497514255040514]
This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment.
We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes.
Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2021-05-03T07:23:39Z) - Learning to Continuously Optimize Wireless Resource In Episodically
Dynamic Environment [55.91291559442884]
This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment.
We propose to build the notion of continual learning into the modeling process of learning wireless systems.
Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2020-11-16T08:24:34Z) - Trajectory-wise Multiple Choice Learning for Dynamics Generalization in
Reinforcement Learning [137.39196753245105]
We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization.
We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector.
Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
arXiv Detail & Related papers (2020-10-26T03:20:42Z) - Context-aware Dynamics Model for Generalization in Model-Based
Reinforcement Learning [124.9856253431878]
We decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it.
In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics.
The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.
arXiv Detail & Related papers (2020-05-14T08:10:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.