PyTorchKR Papers

최신 논문

총 1,516편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2503.14119

Decentralized Continuification Control of Multi-Agent Systems via Distributed Density Estimation

This paper introduces a novel decentralized implementation of a continuification-based strategy to control the density of large-scale multi-agent systems on the unit circle. While continuification methods effectively address micro-to-macro control problems by reformulating ordinary/stochastic differential equations (ODEs/SDEs) agent-based models into more tractable partial differential equations (PDEs), they traditionally require centralized knowledge of macroscopic state observables. We overcome this limitation by developing a distributed density estimation framework that combines kernel density estimation with PI consensus dynamics. Our approach enables agents to compute local density estimates and derive local control actions using only information from neighboring agents in a communication network. Numerical validations across multiple scenarios - including regulation, tracking, and time-varying communication topologies - confirm the effectiveness of the proposed approach. They also convincingly demonstrate that our decentralized implementation achieves performance comparable to centralized approaches while enhancing reliability and practical applicability.

arXiv:2503.09887

On the contraction properties of Sinkhorn semigroups

We develop a novel semigroup contraction analysis based on Lyapunov techniques to prove the exponential convergence of Sinkhorn equations on weighted Banach spaces. This operator-theoretic framework yields exponential decays of Sinkhorn iterates towards Schr\"odinger bridges with respect to general classes of $\phi$-divergences as well as in weighted Banach spaces. To the best of our knowledge, these are the first results of this type in the literature on entropic transport and the Sinkhorn algorithm. We also illustrate the impact of these results in the context of multivariate linear Gaussian models as well as statistical finite mixture models including Gaussian-kernel density estimation of complex data distributions arising in generative models.

arXiv:2503.10232공식 코드 · Papers with Code

Flows on convex polytopes

We present a framework for modeling complex, high-dimensional distributions on convex polytopes by leveraging recent advances in discrete and continuous normalizing flows on Riemannian manifolds. We show that any full-dimensional polytope is homeomorphic to a unit ball, and our approach harnesses flows defined on the ball, mapping them back to the original polytope. Furthermore, we introduce a strategy to construct flows when only the vertex representation of a polytope is available, employing maximum entropy barycentric coordinates and Aitchison geometry. Our experiments take inspiration from applications in metabolic flux analysis and demonstrate that our methods achieve competitive density estimation, sampling accuracy, as well as fast training and inference times.

arXiv:2503.08141공식 코드 · Papers with Code

Scaling Probabilistic Circuits via Data Partitioning

Probabilistic circuits (PCs) enable us to learn joint distributions over a set of random variables and to perform various probabilistic queries in a tractable fashion. Though the tractability property allows PCs to scale beyond non-tractable models such as Bayesian Networks, scaling training and inference of PCs to larger, real-world datasets remains challenging. To remedy the situation, we show how PCs can be learned across multiple machines by recursively partitioning a distributed dataset, thereby unveiling a deep connection between PCs and federated learning (FL). This leads to federated circuits (FCs) -- a novel and flexible federated learning (FL) framework that (1) allows one to scale PCs on distributed learning environments (2) train PCs faster and (3) unifies for the first time horizontal, vertical, and hybrid FL in one framework by re-framing FL as a density estimation problem over distributed datasets. We demonstrate FC's capability to scale PCs on various large-scale datasets. Also, we show FC's versatility in handling horizontal, vertical, and hybrid FL within a unified framework on multiple classification tasks.

arXiv:2503.08246

Dynamic DBSCAN with Euler Tour Sequences

We propose a fast and dynamic algorithm for Density-Based Spatial Clustering of Applications with Noise (DBSCAN) that efficiently supports online updates. Traditional DBSCAN algorithms, designed for batch processing, become computationally expensive when applied to dynamic datasets, particularly in large-scale applications where data continuously evolves. To address this challenge, our algorithm leverages the Euler Tour Trees data structure, enabling dynamic clustering updates without the need to reprocess the entire dataset. This approach preserves a near-optimal accuracy in density estimation, as achieved by the state-of-the-art static DBSCAN method (Esfandiari et al., 2021) Our method achieves an improved time complexity of $O(d \log^3(n) + \log^4(n))$ for every data point insertion and deletion, where $n$ and $d$ denote the total number of updates and the data dimension, respectively. Empirical studies also demonstrate significant speedups over conventional DBSCANs in real-time clustering of dynamic datasets, while maintaining comparable or superior clustering quality.

arXiv:2503.07021

Learning Energy-Based Models by Self-normalising the Likelihood

Training an energy-based model (EBM) with maximum likelihood is challenging due to the intractable normalisation constant. Traditional methods rely on expensive Markov chain Monte Carlo (MCMC) sampling to estimate the gradient of logartihm of the normalisation constant. We propose a novel objective called self-normalised log-likelihood (SNL) that introduces a single additional learnable parameter representing the normalisation constant compared to the regular log-likelihood. SNL is a lower bound of the log-likelihood, and its optimum corresponds to both the maximum likelihood estimate of the model parameters and the normalisation constant. We show that the SNL objective is concave in the model parameters for exponential family distributions. Unlike the regular log-likelihood, the SNL can be directly optimised using stochastic gradient techniques by sampling from a crude proposal distribution. We validate the effectiveness of our proposed method on various density estimation tasks as well as EBMs for regression. Our results show that the proposed method, while simpler to implement and tune, outperforms existing techniques.

arXiv:2503.06144

Exploring the usage of Probabilistic Neural Networks for Ionospheric electron density estimation

A fundamental limitation of traditional Neural Networks (NN) in predictive modelling is their inability to quantify uncertainty in their outputs. In critical applications like positioning systems, understanding the reliability of predictions is critical for constructing confidence intervals, early warning systems, and effectively propagating results. For instance, Precise Point Positioning in satellite navigation heavily relies on accurate error models for ancillary data (orbits, clocks, ionosphere, and troposphere) to compute precise error estimates. In addition, these uncertainty estimates are needed to establish robust protection levels in safety critical applications. To address this challenge, the main objectives of this paper aims at exploring a potential framework capable of providing both point estimates and associated uncertainty measures of ionospheric Vertical Total Electron Content (VTEC). In this context, Probabilistic Neural Networks (PNNs) offer a promising approach to achieve this goal. However, constructing an effective PNN requires meticulous design of hidden and output layers, as well as careful definition of prior and posterior probability distributions for network weights and biases. A key finding of this study is that the uncertainty provided by the PNN model in VTEC estimates may be systematically underestimated. In low-latitude areas, the actual error was observed to be as much as twice the model's estimate. This underestimation is expected to be more pronounced during solar maximum, correlating with increased VTEC values.

arXiv:2503.06697

Diffusion Model Based Probabilistic Day-ahead Load Forecasting

Accurate probabilistic load forecasting is crucial for maintaining the safety and stability of power systems. However, the mainstream approach, multi-step prediction, must be improved by cumulative errors and latency issues, which limits its effectiveness in probabilistic day-ahead load forecasting (PDALF). To overcome these challenges, we introduce DALNet, a novel denoising diffusion model designed to generate load curves rather than relying on direct prediction. By shifting the focus to curve generation, DALNet captures the complex distribution of actual load time-series data under specific conditions with greater fidelity. To further enhance DALNet, we propose the temporal multi-scale attention block (TMSAB), a mechanism designed to integrate both positional and temporal information for improved forecasting precision. Furthermore, we utilize kernel density estimation (KDE) to reconstruct the distribution of generated load curves and employ KL divergence to compare them with the actual data distribution. Experimental results demonstrate that DALNet excels in load forecasting accuracy and offers a novel perspective for other predictive tasks within power systems.

arXiv:2502.19781

RANGE: Retrieval Augmented Neural Fields for Multi-Resolution Geo-Embeddings

The choice of representation for geographic location significantly impacts the accuracy of models for a broad range of geospatial tasks, including fine-grained species classification, population density estimation, and biome classification. Recent works like SatCLIP and GeoCLIP learn such representations by contrastively aligning geolocation with co-located images. While these methods work exceptionally well, in this paper, we posit that the current training strategies fail to fully capture the important visual features. We provide an information theoretic perspective on why the resulting embeddings from these methods discard crucial visual information that is important for many downstream tasks. To solve this problem, we propose a novel retrieval-augmented strategy called RANGE. We build our method on the intuition that the visual features of a location can be estimated by combining the visual features from multiple similar-looking locations. We evaluate our method across a wide variety of tasks. Our results show that RANGE outperforms the existing state-of-the-art models with significant margins in most tasks. We show gains of up to 13.1\% on classification tasks and 0.145 $R^2$ on regression tasks. All our code will be released on GitHub. Our models will be released on HuggingFace.

arXiv:2502.19605

Mixture models for data with unknown distributions

We describe and analyze a broad class of mixture models for real-valued multivariate data in which the probability density of observations within each component of the model is represented as an arbitrary combination of basis functions. Fits to these models give us a way to cluster data with distributions of unknown form, including strongly non-Gaussian or multimodal distributions, and return both a division of the data and an estimate of the distributions, effectively performing clustering and density estimation within each cluster at the same time. We describe two fitting methods, one using an expectation-maximization (EM) algorithm and the other a Bayesian non-parametric method using a collapsed Gibbs sampler. The former is numerically efficient, but gives only point estimates of the probability densities. The latter is more computationally demanding but returns a full Bayesian posterior and also an estimate of the number of components. We demonstrate our methods with a selection of illustrative applications and give code implementing both algorithms.

arXiv:2502.17690

A Fokker-Planck-Based Loss Function that Bridges Dynamics with Density Estimation

We have derived a novel loss function from the Fokker-Planck equation that links dynamical system models with their probability density functions, demonstrating its utility in model identification and density estimation. In the first application, we show that this loss function can enable the extraction of dynamical parameters from non-temporal datasets, including timestamp-free measurements from steady non-equilibrium systems such as noisy Lorenz systems and gene regulatory networks. In the second application, when coupled with a density estimator, this loss facilitates density estimation when the dynamic equations are known. For density estimation, we propose a density estimator that integrates a Gaussian Mixture Model with a normalizing flow model. It simultaneously estimates normalized density, energy, and score functions from both empirical data and dynamics. It is compatible with a variety of data-based training methodologies, including maximum likelihood and score matching. It features a latent space akin to a modern Hopfield network, where the inherent Hopfield energy effectively assigns low densities to sparsely populated data regions, addressing common challenges in neural density estimators. Additionally, this Hopfield-like energy enables direct and rapid data manipulation through the Concave-Convex Procedure (CCCP) rule, facilitating tasks such as denoising and clustering. Our work demonstrates a principled framework for leveraging the complex interdependencies between dynamics and density estimation, as illustrated through synthetic examples that clarify the underlying theoretical intuitions.

arXiv:2502.15756

Causal Covariate Shift Correction using Fisher information penalty

Evolving feature densities across batches of training data bias cross-validation, making model selection and assessment unreliable (\cite{sugiyama2012machine}). This work takes a distributed density estimation angle to the training setting where data are temporally distributed. \textit{Causal Covariate Shift Correction ($C^{3}$)}, accumulates knowledge about the data density of a training batch using Fisher Information, and using it to penalize the loss in all subsequent batches. The penalty improves accuracy by $12.9\%$ over the full-dataset baseline, by $20.3\%$ accuracy at maximum in batchwise and $5.9\%$ at minimum in foldwise benchmarks.

arXiv:2502.16232

Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems

Bayesian filtering for high-dimensional nonlinear stochastic dynamical systems is a fundamental yet challenging problem in many fields of science and engineering. Existing methods face significant obstacles: Gaussian-based filters struggle with non-Gaussian distributions, while sequential Monte Carlo methods are computationally intensive and prone to particle degeneracy in high dimensions. Although generative models in machine learning have made significant progress in modeling high-dimensional non-Gaussian distributions, their inefficiency in online updating limits their applicability to filtering problems. To address these challenges, we propose a flow-based Bayesian filter (FBF) that integrates normalizing flows to construct a novel latent linear state-space model with Gaussian filtering distributions. This framework facilitates efficient density estimation and sampling using invertible transformations provided by normalizing flows, and it enables the construction of filters in a data-driven manner, without requiring prior knowledge of system dynamics or observation models. Numerical experiments demonstrate the superior accuracy and efficiency of FBF.

arXiv:2502.12949

Efficient Learning Under Density Shift in Incremental Settings Using Cramér-Rao-Based Regularization

The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenges that exist at the algorithmic level. With growing interest in automating the learning loop, training with data that arrive in a sequence rather than in the classical in-memory training data form will face a machine learning challenge because of evolving feature distributions across batches of training data biasing the cross-validation step (\cite{sugiyama2012machine}). This work takes a distributed density estimation angle to the problem where data are temporally distributed. It processes data in batches and allows a neural network to treat a batch as training data. The method accumulates knowledge about the data density via posterior probability absorption using the Fisher Information Matrix, which contains information about the local optimization gradients for the batch. This is then used as a regularizer for the loss in the following batch, and therefore the density estimate for the entire dataset constructively gets more robust to the non-iid distribution shift. This needs the presence of a pair of batches in memory at a time, so the space cost is not a function of the size of the complete, distributed dataset. We proposed a novel regularization-based approach Covariate Shift Correction $C^{2}A$ that leverages Fisher information and Kullback-Leibler divergence to adapt to both natural and sequential covariate shift caused by dataset fragmentation. $C^{2}A$ achieves $19\%$ accuracy at maximum against state-of-the-art methods.

arXiv:2502.13825

Mixup Regularization: A Probabilistic Perspective

In recent years, mixup regularization has gained popularity as an effective way to improve the generalization performance of deep learning models by training on convex combinations of training data. While many mixup variants have been explored, the proper adoption of the technique to conditional density estimation and probabilistic machine learning remains relatively unexplored. This work introduces a novel framework for mixup regularization based on probabilistic fusion that is better suited for conditional density estimation tasks. For data distributed according to a member of the exponential family, we show that likelihood functions can be analytically fused using log-linear pooling. We further propose an extension of probabilistic mixup, which allows for fusion of inputs at an arbitrary intermediate layer of the neural network. We provide a theoretical analysis comparing our approach to standard mixup variants. Empirical results on synthetic and real datasets demonstrate the benefits of our proposed framework compared to existing mixup variants.

arXiv:2502.13394

Flow-based generative models as iterative algorithms in probability space

Generative AI (GenAI) has revolutionized data-driven modeling by enabling the synthesis of high-dimensional data across various applications, including image generation, language modeling, biomedical signal processing, and anomaly detection. Flow-based generative models provide a powerful framework for capturing complex probability distributions, offering exact likelihood estimation, efficient sampling, and deterministic transformations between distributions. These models leverage invertible mappings governed by Ordinary Differential Equations (ODEs), enabling precise density estimation and likelihood evaluation. This tutorial presents an intuitive mathematical framework for flow-based generative models, formulating them as neural network-based representations of continuous probability densities. We explore key theoretical principles, including the Wasserstein metric, gradient flows, and density evolution governed by ODEs, to establish convergence guarantees and bridge empirical advancements with theoretical insights. By providing a rigorous yet accessible treatment, we aim to equip researchers and practitioners with the necessary tools to effectively apply flow-based generative models in signal processing and machine learning.

arXiv:2502.11927

Continual Learning Should Move Beyond Incremental Classification

Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental classification tasks, where models learn to classify new categories while retaining knowledge of previously learned ones. Here, we argue that maintaining such a focus limits both theoretical development and practical applicability of CL methods. Through a detailed analysis of concrete examples - including multi-target classification, robotics with constrained output spaces, learning in continuous task domains, and higher-level concept memorization - we demonstrate how current CL approaches often fail when applied beyond standard classification. We identify three fundamental challenges: (C1) the nature of continuity in learning problems, (C2) the choice of appropriate spaces and metrics for measuring similarity, and (C3) the role of learning objectives beyond classification. For each challenge, we provide specific recommendations to help move the field forward, including formalizing temporal dynamics through distribution processes, developing principled approaches for continuous task spaces, and incorporating density estimation and generative objectives. In so doing, this position paper aims to broaden the scope of CL research while strengthening its theoretical foundations, making it more applicable to real-world problems.

arXiv:2502.10505

Preference learning made easy: Everything should be understood through win rate

Preference learning, or the task of aligning generative models to preference comparison data, has yet to reach the conceptual maturity of classification, density estimation, etc. To close this gap, this work presents a framework to understand preference learning starting from the sampling distribution of pairwise preference data. First, we prove that the only evaluation of a generative model that respects both preferences and prevalences in the data distribution is a form of win rate, justifying win rate as the focal point to understand preference learning. We then analyze preference learning methods as win rate optimization (WRO) or non-WRO. We present novel instances of WRO beyond existing examples (RLHF, NLHF) and identify two key theoretical benefits of all such methods. We prove that common non-WRO methods like DPO and SFT on preferred samples lack these properties and suggest ways to mitigate such theoretical limitations. We also show that WRO underperforms in practice due optimization difficulties and that optimization success predicts performance better than choices which affect the objective's solution. Our analysis highlights best practices for existing methods and provides recommendations for future research, guided by the principle that one should either align non-WRO methods more closely with WRO or improve the optimization of WRO objectives.

arXiv:2502.06829

Convolution-Based Converter : A Weak-Prior Approach For Modeling Stochastic Processes Based On Conditional Density Estimation

In this paper, a Convolution-Based Converter (CBC) is proposed to develop a methodology for removing the strong or fixed priors in estimating the probability distribution of targets based on observations in the stochastic process. Traditional approaches, e.g., Markov-based and Gaussian process-based methods, typically leverage observations to estimate targets based on strong or fixed priors (such as Markov properties or Gaussian prior). However, the effectiveness of these methods depends on how well their prior assumptions align with the characteristics of the problem. When the assumed priors are not satisfied, these approaches may perform poorly or even become unusable. To overcome the above limitation, we introduce the Convolution-Based converter (CBC), which implicitly estimates the conditional probability distribution of targets without strong or fixed priors, and directly outputs the expected trajectory of the stochastic process that satisfies the constraints from observations. This approach reduces the dependence on priors, enhancing flexibility and adaptability in modeling stochastic processes when addressing different problems. Experimental results demonstrate that our method outperforms existing baselines across multiple metrics.

arXiv:2502.07580공식 코드 · Papers with Code

Generative Modeling with Bayesian Sample Inference

We derive a novel generative model from iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we can formulate the sampling process in the language of Bayesian probability. Our model uses a sequence of prediction and posterior update steps to iteratively narrow down the unknown sample starting from a broad initial belief. In addition to a rigorous theoretical analysis, we establish a connection between our model and diffusion models and show that it includes Bayesian Flow Networks (BFNs) as a special case. In our experiments, we demonstrate that our model improves sample quality on ImageNet32 over both BFNs and the closely related Variational Diffusion Models, while achieving equivalent log-likelihoods on ImageNet32 and CIFAR10. Find our code at https://github.com/martenlienen/bsi.