Related papers: Multi-Operational Mathematical Derivations in Latent Space

Related papers

Intriguing Properties of Dynamic Sampling Networks [0.0]
We develop and analyze a novel operator which generalizes existing methods, which we term "warping"<n>Warping provides a minimal implementation of dynamic sampling which is amenable to analysis.<n>We show that these mechanisms represent an entirely different class of operators to the traditional translationally invariant operators defined by convolutions.
arXiv Detail & Related papers (2025-11-25T19:40:36Z)
A Deep Learning Framework for Multi-Operator Learning: Architectures and Approximation Theory [2.2731895181875346]
We study the problem of learning collections of operators and provide both theoretical and empirical advances.<n>We distinguish between two regimes: (i) multiple operator learning, where a single network represents a continuum of operators parameterized by a parametric function, and (ii) learning several distinct single operators, where each operator is learned independently.<n>Overall, this work establishes a unified theoretical and practical foundation for scalable operator learning across multiple operators.
arXiv Detail & Related papers (2025-10-29T10:52:02Z)
Data-driven approximation of transfer operators for mean-field stochastic differential equations [0.4473327661758546]
Mean-field differential equations, also called McKean--Vlasov equations, are the limiting equations of particle systems with fully symmetrictemporal potential.<n>This paper shows how extended dynamic mode decomposition and the Galerkin projection methodology can be used to compute finite-dimensional approximations of McKean--Vlasov equations.
arXiv Detail & Related papers (2025-09-11T23:06:48Z)
Multi-Operator Few-Shot Learning for Generalization Across PDE Families [17.225653683970393]
We propose a unified framework for multi-operator few-shot learning, which aims to generalize to unseen PDE operators.<n>Our method integrates three key components: (i) multi-task self-supervised pretraining of a shared Fourier Neural Operator (FNO) encoder, (ii) text-conditioned operator embeddings derived from statistical summaries of input-output fields, and (iii) memory-augmented multimodal prompting.<n> Experiments on PDE benchmarks, including Darcy Flow and Navier Stokes variants, demonstrate that our model outperforms existing operator learning baselines in few-shot generalization.
arXiv Detail & Related papers (2025-08-02T06:00:01Z)
Directional Non-Commutative Monoidal Structures for Compositional Embeddings in Machine Learning [0.0]
We introduce a new structure for compositional embeddings built on directional non-commutative monoidal operators.<n>Our construction defines a distinct composition operator circ_i for each axis i, ensuring associative combination along each axis without imposing global commutativity.<n>All axis-specific operators commute with one another, enforcing a global interchange law that enables consistent crossaxis compositions.
arXiv Detail & Related papers (2025-05-21T13:27:14Z)
Manifold Learning with Normalizing Flows: Towards Regularity, Expressivity and Iso-Riemannian Geometry [8.020732438595905]
This work focuses on addressing distortions and modeling errors that can arise in the multi-modal setting.<n>We showcase the effectiveness of the synergy of the proposed approaches in several numerical experiments with both synthetic and real data.
arXiv Detail & Related papers (2025-05-12T21:44:42Z)
Operator Learning: A Statistical Perspective [17.98959620987217]
Operator learning has emerged as a powerful tool in scientific computing for approximating mappings between infinite-dimensional function spaces. We begin by formalizing operator learning as a function-to-function regression problem and review some recent developments in the field. We also discuss strategies for incorporating physical and mathematical constraints into architecture design and training processes.
arXiv Detail & Related papers (2025-04-04T14:58:45Z)
Connecting the geometry and dynamics of many-body complex systems with message passing neural operators [1.8434042562191815]
We introduce a scalable AI framework, ROMA, for learning multiscale evolution operators of many-body complex systems. An attention mechanism is used to model multiscale interactions by connecting geometric representations of local subgraphs and dynamical operators. We demonstrate that the ROMA framework improves scalability and positive transfer between forecasting and effective dynamics tasks.
arXiv Detail & Related papers (2025-02-21T20:04:09Z)
A Mathematical Analysis of Neural Operator Behaviors [0.0]
This paper presents a rigorous framework for analyzing the behaviors of neural operators. We focus on their stability, convergence, clustering dynamics, universality, and generalization error. We aim to offer clear and unified guidance in a single setting for the future design of neural operator-based methods.
arXiv Detail & Related papers (2024-10-28T19:38:53Z)
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism [68.05754701230039]
We construct a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models.<n>We propose a random matrix-based algorithm to enhance the model's reasoning ability.
arXiv Detail & Related papers (2024-05-24T07:41:26Z)
Operator Learning: Algorithms and Analysis [8.305111048568737]
Operator learning refers to the application of ideas from machine learning to approximate operators mapping between Banach spaces of functions. This review focuses on neural operators, built on the success of deep neural networks in the approximation of functions defined on finite dimensional Euclidean spaces.
arXiv Detail & Related papers (2024-02-24T04:40:27Z)
A Thorough Examination of Decoding Methods in the Era of LLMs [72.65956436513241]
Decoding methods play an indispensable role in converting language models from next-token predictors into practical task solvers. This paper provides a comprehensive and multifaceted analysis of various decoding methods within the context of large language models. Our findings reveal that decoding method performance is notably task-dependent and influenced by factors such as alignment, model size, and quantization.
arXiv Detail & Related papers (2024-02-10T11:14:53Z)
Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
arXiv Detail & Related papers (2024-02-09T07:18:06Z)
Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders [5.037881619912574]
In this paper, we investigate latent space separation methods for structural syntactic injection in Transformer-based VAEs. Specifically, we explore how syntactic structures can be leveraged in the encoding stage through the integration of graph-based and sequential models. Our empirical evaluation, carried out on natural language sentences and mathematical expressions, reveals that the proposed end-to-end VAE architecture can result in a better overall organisation of the latent space.
arXiv Detail & Related papers (2023-11-14T22:47:23Z)
Enhancing Deep Learning Models through Tensorization: A Comprehensive Survey and Framework [0.0]
This paper explores the steps involved in multidimensional data sources, various multiway analysis methods employed, and the benefits of these approaches. A small example of Blind Source Separation (BSS) is presented comparing 2-dimensional algorithms and a multiway algorithm in Python. Results indicate that multiway analysis is more expressive.
arXiv Detail & Related papers (2023-09-05T17:56:22Z)
Dynamic Latent Separation for Deep Learning [67.62190501599176]
A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
arXiv Detail & Related papers (2022-10-07T17:56:53Z)
Join-Chain Network: A Logical Reasoning View of the Multi-head Attention in Transformer [59.73454783958702]
We propose a symbolic reasoning architecture that chains many join operators together to model output logical expressions. In particular, we demonstrate that such an ensemble of join-chains can express a broad subset of ''tree-structured'' first-order logical expressions, named FOET. We find that the widely used multi-head self-attention module in transformer can be understood as a special neural operator that implements the union bound of the join operator in probabilistic predicate space.
arXiv Detail & Related papers (2022-10-06T07:39:58Z)
Spatiotemporal Analysis Using Riemannian Composition of Diffusion Operators [11.533336104503311]
We assume the variables pertain to some geometry and present an operator-based approach for time-series analysis. Our approach combines three components that are often considered separately: (i) manifold for learning operators representing the geometry of the matrices, (ii) symmetric positive-definite geometry for multiscale composition of operators corresponding to different time samples, and (iii) spectral analysis of the composite operators for extracting different dynamic modes.
arXiv Detail & Related papers (2022-01-21T03:52:33Z)
Multi-Agent Imitation Learning with Copulas [102.27052968901894]
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
arXiv Detail & Related papers (2021-07-10T03:49:41Z)
Redefining Neural Architecture Search of Heterogeneous Multi-Network Models by Characterizing Variation Operators and Model Components [71.03032589756434]
We investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models. We characterize both the variation operators, according to their effect on the complexity and performance of the model; and the models, relying on diverse metrics which estimate the quality of the different parts composing it.
arXiv Detail & Related papers (2021-06-16T17:12:26Z)
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms [71.62575565990502]
We prove that the generalization error of an optimization algorithm can be bounded on the complexity' of the fractal structure that underlies its generalization measure. We further specialize our results to specific problems (e.g., linear/logistic regression, one hidden/layered neural networks) and algorithms.
arXiv Detail & Related papers (2021-06-09T08:05:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.