Peer Revenue Equity in science

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Machine Learning

cs.LG Watch Machine Learning (sign in to use)

Saturday 13 December

Machine Learning

Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction

Integrating domain knowledge into deep learning has emerged as a promising direction for improving model interpretability, generalization, and data efficiency. In this work, we present a novel knowledge-guided ViT-based Masked Autoencoder that embeds scientific domain knowledge within the self-supervised reconstruction process. Instead of relying solely on data-driven optimization, our proposed approach incorporates the Linear Spectral Mixing Model (LSMM) as a physical constraint and physically-based Spectral Angle Mapper (SAM), ensuring that learned representations adhere to known structural relationships between observed signals and their latent components. The framework jointly optimizes LSMM and SAM loss with a conventional Huber loss objective, promoting both numerical accuracy and geometric consistency in the feature space. This knowledge-guided design enhances reconstruction fidelity, stabilizes training under limited supervision, and yields interpretable latent representations grounded in physical principles. The experimental findings indicate that the proposed model substantially enhances reconstruction quality and improves downstream task performance, highlighting the promise of embedding physics-informed inductive biases within transformer-based self-supervised learning.
Read the full abstract

All authors Abdul Matin, Rupasree Dey, Tanjim Bin Faruk, Shrideep Pallickara, Sangmi Lee Pallickara

Machine Learning · Cross-listed from stat.ML

Efficient Level-Crossing Probability Calculation for Gaussian Process Modeled Data

Almost all scientific data have uncertainties originating from different sources. Gaussian process regression (GPR) models are a natural way to model data with Gaussian-distributed uncertainties. GPR also has the benefit of reducing I/O bandwidth and storage requirements for large scientific simulations. However, the reconstruction from the GPR models suffers from high computation complexity. To make the situation worse, classic approaches for visualizing the data uncertainties, like probabilistic marching cubes, are also computationally very expensive, especially for data of high resolutions. In this paper, we accelerate the level-crossing probability calculation efficiency on GPR models by subdividing the data spatially into a hierarchical data structure and only reconstructing values adaptively in the regions that have a non-zero probability. For each region, leveraging the known GPR kernel and the saved data observations, we propose a novel approach to efficiently calculate an upper bound for the level-crossing probability inside the region and use this upper bound to make the subdivision and reconstruction decisions. We demonstrate that our value occurrence probability estimation is accurate with a low computation cost by experiments that calculate the level-crossing probability fields on different datasets.
Read the full abstract

All authors Haoyu Li, Isaac J Michaud, Ayan Biswas, Han-Wei Shen

Machine Learning · Cross-listed from cs.RO

Sim2Real Reinforcement Learning for Soccer skills

This thesis work presents a more efficient and effective approach to training control-related tasks for humanoid robots using Reinforcement Learning (RL). The traditional RL methods are limited in adapting to real-world environments, complexity, and natural motions, but the proposed approach overcomes these limitations by using curriculum training and Adversarial Motion Priors (AMP) technique. The results show that the developed RL policies for kicking, walking, and jumping are more dynamic, and adaptive, and outperformed previous methods. However, the transfer of the learned policy from simulation to the real world was unsuccessful, highlighting the limitations of current RL methods in fully adapting to real-world scenarios.
Read the full abstract

Machine Learning

Rough Sets for Explainability of Spectral Graph Clustering

Graph Spectral Clustering methods (GSC) allow representing clusters of diverse shapes, densities, etc. However, the results of such algorithms, when applied e.g. to text documents, are hard to explain to the user, especially due to embedding in the spectral space which has no obvious relation to document contents. Furthermore, the presence of documents without clear content meaning and the stochastic nature of the clustering algorithms deteriorate explainability. This paper proposes an enhancement to the explanation methodology, proposed in an earlier research of our team. It allows us to overcome the latter problems by taking inspiration from rough set theory.
Read the full abstract

All authors Bartłomiej Starosta, Sławomir T. Wierzchoń, Piotr Borkowski, Dariusz Czerski, Marcin Sydow, Eryk Laskowski, Mieczysław A. Kłopotek

Machine Learning · Cross-listed from stat.ML

Co-Hub Node Based Multiview Graph Learning with Theoretical Guarantees

Identifying the graphical structure underlying the observed multivariate data is essential in numerous applications. Current methodologies are predominantly confined to deducing a singular graph under the presumption that the observed data are uniform. However, many contexts involve heterogeneous datasets that feature multiple closely related graphs, typically referred to as multiview graphs. Previous research on multiview graph learning promotes edge-based similarity across layers using pairwise or consensus-based regularizers. However, multiview graphs frequently exhibit a shared node-based architecture across different views, such as common hub nodes. Such commonalities can enhance the precision of learning and provide interpretive insight. In this paper, we propose a co-hub node model, positing that different views share a common group of hub nodes. The associated optimization framework is developed by enforcing structured sparsity on the connections of these co-hub nodes. Moreover, we present a theoretical examination of layer identifiability and determine bounds on estimation error. The proposed methodology is validated using both synthetic graph data and fMRI time series data from multiple subjects to discern several closely related graphs.
Read the full abstract

All authors Bisakh Banerjee, Mohammad Alwardat, Tapabrata Maiti, Selin Aviyente

Machine Learning · Cross-listed from math.DS

Data-driven modelling of autonomous and forced dynamical systems

The paper demonstrates that invariant foliations are accurate, data-efficient and practical tools for data-driven modelling of physical systems. Invariant foliations can be fitted to data that either fill the phase space or cluster about an invariant manifold. Invariant foliations can be fitted to a single trajectory or multiple trajectories. Over and underfitting are eliminated by appropriately choosing a function representation and its hyperparameters, such as polynomial orders. The paper extends invariant foliations to forced and parameter dependent systems. It is assumed that forcing is provided by a volume preserving map, and therefore the forcing can be periodic, quasi-periodic or even chaotic. The method utilises full trajectories, hence it is able to predict long-term dynamics accurately. We take into account if a forced system is reducible to an autonomous system about a steady state, similar to how Floquet theory guarantees reducibility for periodically forced systems. In order to find an invariant manifold, multiple invariant foliations are calculated in the neighbourhood of the invariant manifold. Some of the invariant foliations can be linear, while others nonlinear but only defined in a small neighbourhood of an invariant manifold, which reduces the number of parameters to be identified. An invariant manifold is recovered as the zero level set of one or more of the foliations. To interpret the results, the identified mathematical models are transformed to a canonical form and instantaneous frequency and damping information are calculated.
Read the full abstract

Machine Learning

Learning Dynamics in Memristor-Based Equilibrium Propagation

Memristor-based in-memory computing has emerged as a promising paradigm to overcome the constraints of the von Neumann bottleneck and the memory wall by enabling fully parallelisable and energy-efficient vector-matrix multiplications. We investigate the effect of nonlinear, memristor-driven weight updates on the convergence behaviour of neural networks trained with equilibrium propagation (EqProp). Six memristor models were characterised by their voltage-current hysteresis and integrated into the EBANA framework for evaluation on two benchmark classification tasks. EqProp can achieve robust convergence under nonlinear weight updates, provided that memristors exhibit a sufficiently wide resistance range of at least an order of magnitude.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics

Infographic Visual Question Answering (InfographicVQA) evaluates a model's ability to read and reason over data-rich, layout-heavy visuals that combine text, charts, icons, and design elements. Compared with scene-text or natural-image VQA, infographics require stronger integration of OCR, layout understanding, and numerical and semantic reasoning. We introduce ViInfographicVQA, the first benchmark for Vietnamese InfographicVQA, comprising over 6747 real-world infographics and 20409 human-verified question-answer pairs across economics, healthcare, education, and more. The benchmark includes two evaluation settings. The Single-image task follows the traditional setup in which each question is answered using a single infographic. The Multi-image task requires synthesizing evidence across multiple semantically related infographics and is, to our knowledge, the first Vietnamese evaluation of cross-image reasoning in VQA. We evaluate a range of recent vision-language models on this benchmark, revealing substantial performance disparities, with the most significant errors occurring on Multi-image questions that involve cross-image integration and non-span reasoning. ViInfographicVQA contributes benchmark results for Vietnamese InfographicVQA and sheds light on the limitations of current multimodal models in low-resource contexts, encouraging future exploration of layout-aware and cross-image reasoning methods.
Read the full abstract

All authors Tue-Thu Van-Dinh, Hoang-Duy Tran, Truong-Binh Duong, Mai-Hanh Pham, Binh-Nam Le-Nguyen, Quoc-Thai Nguyen

Machine Learning

Can Graphs Improve Tabular Foundation Models?

Tabular data are central to many real-world systems. While recent tabular transformers and in-context learners such as SAINT, TP-BERTa, TabPFN, TabICL, and MITRA incorporate limited inter-row reasoning, most approaches still lack an explicit mechanism to model relationships among instances, even though similar samples often share related outcomes. We investigate whether introducing simple graph priors can enhance pretrained tabular transformers. Concretely, we introduce {BOLERO}, a lightweight, static bipartite graph head that augments {RoBERTa-Tab} (a RoBERTa-style tabular backbone pretrained with masked-token prediction.) Each instance connects to feature/value anchors; a small GNN refines row representations, while the backbone remains frozen. We evaluate on 80 classification and 64 regression datasets from the TP-BERTa benchmark suites, comparing against strong baselines including XGBoost, CatBoost, TabPFN-v2, MITRA, TabICL, TP-BERTa, and RoBERTa-Tab. To ensure statistically sound conclusions, we follow best practices for multi-dataset evaluation: pairwise Wilcoxon signed-rank tests on per-dataset score differences and effect sizes (median improvement with confidence intervals), rather than mean-rank post-hoc tests that depend on the competitor pool. BOLERO achieves the highest number of statistically significant wins across both classification and regression, demonstrating that lightweight graph priors meaningfully improve pretrained tabular transformers.
Read the full abstract

All authors Franck Le, Keith Grueneberg, Erich Nahum, Vadim Sheinin

Machine Learning

DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields

We present DeepVekua, a hybrid architecture that unifies geometric deep learning with spectral analysis to solve partial differential equations (PDEs) in sparse data regimes. By learning a diffeomorphic coordinate transformation that maps complex geometries to a latent harmonic space, our method outperforms state-of-the-art implicit representations on advection-diffusion systems. Unlike standard coordinate-based networks which struggle with spectral bias, DeepVekua separates the learning of geometry from the learning of physics, solving for optimal spectral weights in closed form. We demonstrate a 100x improvement over spectral baselines. The code is available at https://github.com/VladimerKhasia/vekuanet.
Read the full abstract

Machine Learning

Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment

Group Relative Policy Optimization (GRPO) has proven highly effective in enhancing the alignment capabilities of Large Language Models (LLMs). However, current adaptations of GRPO for the flow matching-based image generation neglect a foundational conflict between its core principles and the distinct dynamics of the visual synthesis process. This mismatch leads to two key limitations: (i) Uniformly applying a sparse terminal reward across all timesteps impairs temporal credit assignment, ignoring the differing criticality of generation phases from early structure formation to late-stage tuning. (ii) Exclusive reliance on relative, intra-group rewards causes the optimization signal to fade as training converges, leading to the optimization stagnation when reward diversity is entirely depleted. To address these limitations, we propose Value-Anchored Group Policy Optimization (VGPO), a framework that redefines value estimation across both temporal and group dimensions. Specifically, VGPO transforms the sparse terminal reward into dense, process-aware value estimates, enabling precise credit assignment by modeling the expected cumulative reward at each generative stage. Furthermore, VGPO replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal even as reward diversity declines. Extensive experiments on three benchmarks demonstrate that VGPO achieves state-of-the-art image quality while simultaneously improving task-specific accuracy, effectively mitigating reward hacking. Project webpage: https://yawen-shao.github.io/VGPO/.
Read the full abstract

All authors Yawen Shao, Jie Xiao, Kai Zhu, Yu Liu, Wei Zhai, Yang Cao, Zheng-Jun Zha

Machine Learning

The Data Efficiency Frontier of Financial Foundation Models: Scaling Laws from Continued Pretraining

Domain-adaptive pretraining (DAPT) offers a practical path to specializing large language models for high-value domains without full retraining. We conduct an early-stage scaling-law analysis of continued pretraining on U.S. SEC filings, training 1B and 3B-parameter Llama-3.2 models on a 400M-token financial corpus with validation checkpoints at 50M, 100M, 200M, and 400M tokens. Results show consistent improvements in SEC-domain validation loss for both models, with the largest gains occurring within the first 200M tokens and diminishing returns thereafter. Power-law fits reveal shallow exponents, indicating that financial language is highly regular and efficiently learnable under continued pretraining. General-domain validation loss remains effectively unchanged across all token budgets, suggesting minimal drift and no signs of catastrophic forgetting. A data-efficiency frontier further shows that both models move toward improved specialization with negligible mixed-domain degradation. Together, these findings provide early empirical guidance for scaling financial foundation models, suggesting that meaningful domain adaptation can be achieved with comparatively modest token budgets and that larger model scales (7B-70B) remain tractable under projected data requirements.
Read the full abstract

Machine Learning · Cross-listed from cs.IT

ElasticVR: Elastic Task Computing in Multi-User Multi-Connectivity Wireless Virtual Reality (VR) Systems

Diverse emerging VR applications integrate streaming of high fidelity 360 video content that requires ample amounts of computation and data rate. Scalable 360 video tiling enables having elastic VR computational tasks that can be scaled adaptively in computation and data rate based on the available user and system resources. We integrate scalable 360 video tiling in an edge-client wireless multi-connectivity architecture for joint elastic task computation offloading across multiple VR users called ElasticVR. To balance the trade-offs in communication, computation, energy consumption, and QoE that arise herein, we formulate a constrained QoE and energy optimization problem that integrates the multi-user/multi-connectivity action space with the elasticity of VR computational tasks. The ElasticVR framework introduces two multi-agent deep reinforcement learning solutions, namely CPPG and IPPG. CPPG adopts a centralized training and centralized execution approach to capture the coupling between users' communication and computational demands. This leads to globally coordinated decisions at the cost of increased computational overheads and limited scalability. To address the latter challenges, we also explore an alternative strategy denoted IPPG that adopts a centralized training with decentralized execution paradigm. IPPG leverages shared information and parameter sharing to learn robust policies; however, during execution, each user takes action independently based on its local state information only. The decentralized execution alleviates the communication and computation overhead of centralized decision-making and improves scalability. We show that the ElasticVR framework improves the PSNR by 43.21%, while reducing the response time and energy consumption by 42.35% and 56.83%, respectively, compared with a case where no elasticity is incorporated into VR computations.
Read the full abstract

Machine Learning

Synthetic Swarm Mosquito Dataset for Acoustic Classification: A Proof of Concept

Mosquito-borne diseases pose a serious global health threat, causing over 700,000 deaths annually. This work introduces a proof-of-concept Synthetic Swarm Mosquito Dataset for Acoustic Classification, created to simulate realistic multi-species and noisy swarm conditions. Unlike conventional datasets that require labor-intensive recording of individual mosquitoes, the synthetic approach enables scalable data generation while reducing human resource demands. Using log-mel spectrograms, we evaluated lightweight deep learning architectures for the classification of mosquito species. Experiments show that these models can effectively identify six major mosquito vectors and are suitable for deployment on embedded low-power devices. The study demonstrates the potential of synthetic swarm audio datasets to accelerate acoustic mosquito research and enable scalable real-time surveillance solutions.
Read the full abstract

All authors Thai-Duy Dinh, Minh-Luan Vo, Cuong Tuan Nguyen, Bich-Hien Vo

Machine Learning · Cross-listed from stat.ML

Towards a pretrained deep learning estimator of the Linfoot informational correlation

We develop a supervised deep-learning approach to estimate mutual information between two continuous random variables. As labels, we use the Linfoot informational correlation, a transformation of mutual information that has many important properties. Our method is based on ground truth labels for Gaussian and Clayton copulas. We compare our method with estimators based on kernel density, k-nearest neighbours and neural estimators. We show generally lower bias and lower variance. As a proof of principle, future research could look into training the model with a more diverse set of examples from other copulas for which ground truth labels are available.
Read the full abstract

All authors Stéphanie M. van den Berg, Ulrich Halekoh, Sören Möller, Andreas Kryger Jensen, Jacob von Bornemann Hjelmborg

Machine Learning

Uncertainty Quantification for Machine Learning: One Size Does Not Fit All

Proper quantification of predictive uncertainty is essential for the use of machine learning in safety-critical applications. Various uncertainty measures have been proposed for this purpose, typically claiming superiority over other measures. In this paper, we argue that there is no single best measure. Instead, uncertainty quantification should be tailored to the specific application. To this end, we use a flexible family of uncertainty measures that distinguishes between total, aleatoric, and epistemic uncertainty of second-order distributions. These measures can be instantiated with specific loss functions, so-called proper scoring rules, to control their characteristics, and we show that different characteristics are useful for different tasks. In particular, we show that, for the task of selective prediction, the scoring rule should ideally match the task loss. On the other hand, for out-of-distribution detection, our results confirm that mutual information, a widely used measure of epistemic uncertainty, performs best. Furthermore, in an active learning setting, epistemic uncertainty based on zero-one loss is shown to consistently outperform other uncertainty measures.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

Unified Control for Inference-Time Guidance of Denoising Diffusion Models

Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diffusion models can be categorized into two main strategies: sampling-based methods, which explore multiple candidate outputs and select those with higher reward signals, and gradient-guided methods, which use differentiable reward approximations to directly steer the generation process. In this work, we propose a universal algorithm, UniCoDe, which brings together the strengths of sampling and gradient-based guidance into a unified framework. UniCoDe integrates local gradient signals during sampling, thereby addressing the sampling inefficiency inherent in complex reward-based sampling approaches. By cohesively combining these two paradigms, UniCoDe enables more efficient sampling while offering better trade-offs between reward alignment and divergence from the diffusion unconditional prior. Empirical results demonstrate that UniCoDe remains competitive with state-of-the-art baselines across a range of tasks. The code is available at https://github.com/maurya-goyal10/UniCoDe
Read the full abstract

Machine Learning · Cross-listed from q-fin.RM

Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall

In the last five years, expected shortfall (ES) and stressed ES (SES) have become key required regulatory measures of market risk in the banking sector, especially following events such as the global financial crisis. Thus, finding ways to optimize their estimation is of great importance. We extend the application of dynamic Bayesian networks (DBNs) to the estimation of 10-day 97.5% ES and stressed ES, building on prior work applying DBNs to value at risk. Using the S&P 500 index as a proxy for the equities trading desk of a US bank, we compare the performance of three DBN structure-learning algorithms with several traditional market risk models, using either the normal or the skewed Student's t return distributions. Backtesting shows that all models fail to produce statistically accurate ES and SES forecasts at the 2.5% level, reflecting the difficulty of modeling extreme tail behavior. For ES, the EGARCH(1,1) model (normal) produces the most accurate forecasts, while, for SES, the GARCH(1,1) model (normal) performs best. All distribution-dependent models deteriorate substantially when using the skewed Student's t distribution. The DBNs perform comparably to the historical simulation model, but their contribution to tail prediction is limited by the small weight assigned to their one-day-ahead forecasts within the return distribution. Future research should examine weighting schemes that enhance the influence of forward-looking DBN forecasts on tail risk estimation.
Read the full abstract

Machine Learning

Eventually LIL Regret: Almost Sure $\ln\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data

We prove that a classic sub-Gaussian mixture proposed by Robbins in a stochastic setting actually satisfies a path-wise (deterministic) regret bound. For every path in a natural “Ville event” $\mathcal E_\alpha$, this regret till time $T$ is bounded by $\ln^2(1/\alpha)/V_T + \ln (1/\alpha) + \ln \ln V_T$ up to universal constants, where $V_T$ is a nonnegative, nondecreasing, cumulative variance process. (The bound reduces to $\ln(1/\alpha) + \ln \ln V_T$ if $V_T \geq \ln(1/\alpha)$.) If the data were stochastic, then one can show that $\mathcal E_\alpha$ has probability at least $1-\alpha$ under a wide class of distributions (eg: sub-Gaussian, symmetric, variance-bounded, etc.). In fact, we show that on the Ville event $\mathcal E_0$ of probability one, the regret on every path in $\mathcal E_0$ is eventually bounded by $\ln \ln V_T$ (up to constants). We explain how this work helps bridge the world of adversarial online learning (which usually deals with regret bounds for bounded data), with game-theoretic statistics (which can handle unbounded data, albeit using stochastic assumptions). In short, conditional regret bounds serve as a bridge between stochastic and adversarial betting.
Read the full abstract

Machine Learning

TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting

TwinFormer is a hierarchical Transformer for long-sequence time-series forecasting. It divides the input into non-overlapping temporal patches and processes them in two stages: (1) a Local Informer with top-$k$ Sparse Attention models intra-patch dynamics, followed by mean pooling; (2) a Global Informer captures long-range inter-patch dependencies using the same top-$k$ attention. A lightweight GRU aggregates the globally contextualized patch tokens for direct multi-horizon prediction. The resulting architecture achieves linear $O(kLd)$ time and memory complexity. On eight real-world benchmarking datasets from six different domains, including weather, stock price, temperature, power consumption, electricity, and disease, and forecasting horizons $96-720$, TwinFormer secures $27$ positions in the top two out of $34$. Out of the $27$, it achieves the best performance on MAE and RMSE at $17$ places and $10$ at the second-best place on MAE and RMSE. This consistently outperforms PatchTST, iTransformer, FEDformer, Informer, and vanilla Transformers. Ablations confirm the superiority of top-$k$ Sparse Attention over ProbSparse and the effectiveness of GRU-based aggregation. Code is available at this repository: https://github.com/Mahimakumavat1205/TwinFormer.
Read the full abstract

Machine Learning · Cross-listed from cs.CV

GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search

Transformer architecture search (TAS) aims to automatically discover efficient vision transformers (ViTs), reducing the need for manual design. Existing TAS methods typically train an over-parameterized network (i.e., a supernet) that encompasses all candidate architectures (i.e., subnets). However, all subnets share the same set of weights, which leads to interference that degrades the smaller subnets severely. We have found that well-trained small subnets can serve as a good foundation for training larger ones. Motivated by this, we propose a progressive training framework, dubbed GrowTAS, that begins with training small subnets and incorporate larger ones gradually. This enables reducing the interference and stabilizing a training process. We also introduce GrowTAS+ that fine-tunes a subset of weights only to further enhance the performance of large subnets. Extensive experiments on ImageNet and several transfer learning benchmarks, including CIFAR-10/100, Flowers, CARS, and INAT-19, demonstrate the effectiveness of our approach over current TAS methods
Read the full abstract

All authors Hyunju Lee, Youngmin Oh, Jeimin Jeon, Donghyeon Baek, Bumsub Ham

Machine Learning · Cross-listed from cs.DC

Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates

Deep Learning Recommendation Models (DLRMs) underpin personalized services but face a critical freshness-accuracy tradeoff due to massive parameter synchronization overheads. Production DLRMs deploy decoupled training/inference clusters, where synchronizing petabyte-scale embedding tables (EMTs) causes multi-minute staleness, degrading recommendation quality and revenue. We observe that (1) inference nodes exhibit sustained CPU underutilization (peak <= 20%), and (2) EMT gradients possess intrinsic low-rank structure, enabling compact update representation. We present LiveUpdate, a system that eliminates inter-cluster synchronization by colocating Low-Rank Adaptation (LoRA) trainers within inference nodes. LiveUpdate addresses two core challenges: (1) dynamic rank adaptation via singular value monitoring to constrain memory overhead (<2% of EMTs), and (2) NUMA-aware resource scheduling with hardware-enforced QoS to eliminate update inference contention (P99 latency impact <20ms). Evaluations show LiveUpdate reduces update costs by 2x versus delta-update baselines while achieving higher accuracy within 1-hour windows. By transforming idle inference resources into freshness engines, LiveUpdate delivers online model updates while outperforming state-of-the-art delta-update methods by 0.04% to 0.24% in accuracy.
Read the full abstract

All authors Wenjun Yu, Sitian Chen, Cheng Chen, Amelie Chi Zhou

Machine Learning · Cross-listed from stat.ME

Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecture

Outlier detection and concept drift detection represent two challenges in data analysis. Most studies address these issues separately. However, joint detection mechanisms in regression remain underexplored, where the continuous nature of output spaces makes distinguishing drifts from outliers inherently challenging. To address this, we propose a novel robust regression framework for joint outlier and concept drift detection. Specifically, we introduce a dual-channel decision process that orchestrates prediction residuals into two coupled logic flows: a rapid response channel for filtering point outliers and a deep analysis channel for diagnosing drifts. We further develop the Exponentially Weighted Moving Absolute Deviation with Distinguishable Types (EWMAD-DT) detector to autonomously differentiate between abrupt and incremental drifts via dynamic thresholding. Comprehensive experiments on both synthetic and real-world datasets demonstrate that our unified framework, enhanced by EWMAD-DT, exhibits superior detection performance even when point outliers and concept drifts coexist.
Read the full abstract

All authors Bingbing Wang, Shengyan Sun, Jiaqi Wang, Yu Tang

Machine Learning

Fractional Differential Equation Physics-Informed Neural Network and Its Application in Battery State Estimation

Accurate estimation of the State of Charge (SOC) is critical for ensuring the safety, reliability, and performance optimization of lithium-ion battery systems. Conventional data-driven neural network models often struggle to fully characterize the inherent complex nonlinearities and memory-dependent dynamics of electrochemical processes, significantly limiting their predictive accuracy and physical interpretability under dynamic operating conditions. To address this challenge, this study proposes a novel neural architecture termed the Fractional Differential Equation Physics-Informed Neural Network (FDIFF-PINN), which integrates fractional calculus with deep learning. The main contributions of this paper include: (1) Based on a fractional-order equivalent circuit model, a discretized fractional-order partial differential equation is constructed. (2) Comparative experiments were conducted using a dynamic charge/discharge dataset of Panasonic 18650PF batteries under multi-temperature conditions (from -10$^{\circ}$C to 20$^{\circ}$C).
Read the full abstract

Machine Learning

Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model

Currently, more and more machine learning (ML) surrogates are being developed for computationally expensive physical models. In this work we investigate the use of a Multi-Fidelity Ensemble Kalman Filter (MF-EnKF) in which the low-fidelity model is such a machine learning surrogate model, instead of a traditional low-resolution or reduced-order model. The idea behind this is to use an ensemble of a few expensive full model runs, together with an ensemble of many cheap but less accurate ML model runs. In this way we hope to reach increased accuracy within the same computational budget. We investigate the performance by testing the approach on two common test problems, namely the Lorenz-2005 model and the Quasi-Geostrophic model. By keeping the original physical model in place, we obtain a higher accuracy than when we completely replace it by the ML model. Furthermore, the MF-EnKF reaches improved accuracy within the same computational budget. The ML surrogate has similar or improved accuracy compared to the low-resolution one, but it can provide a larger speed-up. Our method contributes to increasing the effective ensemble size in the EnKF, which improves the estimation of the initial condition and hence accuracy of the predictions in fields such as meteorology and oceanography.
Read the full abstract

Machine Learning

GRC-Net: Gram Residual Co-attention Net for epilepsy prediction

Prediction of epilepsy based on electroencephalogram (EEG) signals is a rapidly evolving field. Previous studies have traditionally applied 1D processing to the entire EEG signal. However, we have adopted the Gram Matrix method to transform the signals into a 3D representation, enabling modeling of signal relationships across dimensions while preserving the temporal dependencies of the one-dimensional signals. Additionally, we observed an imbalance between local and global signals within the EEG data. Therefore, we introduced multi-level feature extraction, utilizing coattention for capturing global signal characteristics and an inception structure for processing local signals, achieving multi-granular feature extraction. Our experiments on the BONN dataset demonstrate that for the most challenging five-class classification task, GRC-Net achieved an accuracy of 93.66%, outperforming existing methods.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Hellinger loss function for Generative Adversarial Networks

We propose Hellinger-type loss functions for training Generative Adversarial Networks (GANs), motivated by the boundedness, symmetry, and robustness properties of the Hellinger distance. We define an adversarial objective based on this divergence and study its statistical properties within a general parametric framework. We establish the existence, uniqueness, consistency, and joint asymptotic normality of the estimators obtained from the adversarial training procedure. In particular, we analyze the joint estimation of both generator and discriminator parameters, offering a comprehensive asymptotic characterization of the resulting estimators. We introduce two implementations of the Hellinger-type loss and we evaluate their empirical behavior in comparison with the classic (Maximum Likelihood-type) GAN loss. Through a controlled simulation study, we demonstrate that both proposed losses yield improved estimation accuracy and robustness under increasing levels of data contamination.
Read the full abstract

Machine Learning

Optimized Learned Count-Min Sketch

Count-Min Sketch (CMS) is a memory-efficient data structure for estimating the frequency of elements in a multiset. Learned Count-Min Sketch (LCMS) enhances CMS with a machine learning model to reduce estimation error under the same memory usage, but suffers from slow construction due to empirical parameter tuning and lacks theoretical guarantees on intolerable error probability. We propose Optimized Learned Count-Min Sketch (OptLCMS), which partitions the input domain and assigns each partition to its own CMS instance, with CMS parameters analytically derived for fixed thresholds, and thresholds optimized via dynamic programming with approximate feasibility checks. This reduces the need for empirical validation, enabling faster construction while providing theoretical guarantees under these assumptions. OptLCMS also allows explicit control of the allowable error threshold, improving flexibility in practice. Experiments show that OptLCMS builds faster, achieves lower intolerable error probability, and matches the estimation accuracy of LCMS.
Read the full abstract

Machine Learning · Cross-listed from q-fin.TR

Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting

Accurate volatility forecasting is essential in banking, investment, and risk management, because expectations about future market movements directly influence current decisions. This study proposes a hybrid modelling framework that integrates a Stochastic Volatility model with a Long Short Term Memory neural network. The SV model improves statistical precision and captures latent volatility dynamics, especially in response to unforeseen events, while the LSTM network enhances the model's ability to detect complex nonlinear patterns in financial time series. The forecasting is conducted using daily data from the S and P 500 index, covering the period from January 1 1998 to December 31 2024. A rolling window approach is employed to train the model and generate one step ahead volatility forecasts. The performance of the hybrid SV-LSTM model is evaluated through both statistical testing and investment simulations. The results show that the hybrid approach outperforms both the standalone SV and LSTM models and contributes to the development of volatility modelling techniques, providing a foundation for improving risk assessment and strategic investment planning in the context of the S and P 500.
Read the full abstract

Machine Learning · Cross-listed from cs.RO

Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy

Fall recovery is a critical skill for humanoid robots in dynamic environments such as RoboCup, where prolonged downtime often decides the match. Recent techniques using deep reinforcement learning (DRL) have produced robust get-up behaviors, yet existing methods require training of separate policies for each robot morphology. This paper presents a single DRL policy capable of recovering from falls across seven humanoid robots with diverse heights (0.48 - 0.81 m), weights (2.8 - 7.9 kg), and dynamics. Trained with CrossQ, the unified policy transfers zero-shot up to 86 +/- 7% (95% CI [81, 89]) on unseen morphologies, eliminating the need for robot-specific training. Comprehensive leave-one-out experiments, morph scaling analysis, and diversity ablations show that targeted morphological coverage improves zero-shot generalization. In some cases, the shared policy even surpasses the specialist baselines. These findings illustrate the practicality of morphology-agnostic control for fall recovery, laying the foundation for generalist humanoid control. The software is open-source and available at: https://github.com/utra-robosoccer/unified-humanoid-getup
Read the full abstract