Archives AI News

arXiv:2502.07998v2 Announce Type: replace Abstract: Previous influential work showed that infinite width limits of neural networks in the lazy training regime are described by kernel machines. Here, we show that neural networks trained in the rich, feature learning infinite-width regime in two different settings are also described by kernel machines, but with data-dependent kernels. For both cases, we provide explicit expressions for the kernel predictors and prescriptions to numerically calculate them. To derive the first predictor, we study the large-width limit of feature-learning Bayesian networks, showing how feature learning leads to task-relevant adaptation of layer kernels and preactivation densities. The saddle point equations governing this limit result in a min-max optimization problem that defines the kernel predictor. To derive the second predictor, we study gradient flow training of randomly initialized networks trained with weight decay in the infinite-width limit using dynamical mean field theory (DMFT). The fixed point equations of the arising DMFT defines the task-adapted internal representations and the kernel predictor. We compare our kernel predictors to kernels derived from lazy regime and demonstrate that our adaptive kernels achieve lower test loss on benchmark datasets.

arXiv:2509.09088v1 Announce Type: new Abstract: We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of observables defined in [2] is obtained by Riemannian submersion of the balanced manifold. The main technical step is an explicit construction of an orthonormal basis for the tangent space of the balanced manifold using the theory of Jacobi matrices.

arXiv:2506.00795v3 Announce Type: replace Abstract: Recently, supervised learning (SL) methodology has emerged as an effective approach for offline reinforcement learning (RL) due to their simplicity, stability, and efficiency. However, recent studies show that SL methods lack the trajectory stitching capability, typically associated with temporal difference (TD)-based approaches. A question naturally surfaces: textit{How can we endow SL methods with stitching capability and close its performance gap with TD learning?} To answer this question, we introduce $Q$-conditioned maximization supervised learning for offline goal-conditioned RL, which enhances SL with the stitching capability through $Q$-conditioned policy and $Q$-conditioned maximization. Concretely, we propose textbf{G}oal-textbf{C}onditioned textbf{textit{Rein}}forced textbf{S}upervised textbf{L}earning (textbf{GCtextit{Rein}SL}), which consists of (1) estimating the $Q$-function by Normalizing Flows from the offline dataset and (2) finding the maximum $Q$-value within the data support by integrating $Q$-function maximization with Expectile Regression. In inference time, our policy chooses optimal actions based on such a maximum $Q$-value. Experimental results from stitching evaluations on offline RL datasets demonstrate that our method outperforms prior SL approaches with stitching capabilities and goal data augmentation techniques.

arXiv:2509.09119v1 Announce Type: new Abstract: Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments. Low-Rank Adaptation (LoRA), a prominent method within Parameter-Efficient Fine-Tuning (PEFT), has emerged as a promising approach to LLMs by approximating model weight updates using low-rank decomposition. However, LoRA is limited by its uniform rank ( r ) allocation to each incremental matrix, and existing rank allocation techniques aimed at addressing this issue remain computationally inefficient, complex, and unstable, hindering practical applications. To address these limitations, we propose Sensitivity-LoRA, an efficient fine-tuning method that dynamically allocates ranks to weight matrices based on both their global and local sensitivities. It leverages the second-order derivatives (Hessian Matrix) of the loss function to effectively capture weight sensitivity, enabling optimal rank allocation with minimal computational overhead. Our experimental results have demonstrated robust effectiveness, efficiency and stability of Sensitivity-LoRA across diverse tasks and benchmarks.

arXiv:2509.02108v2 Announce Type: replace Abstract: Multi-task learning (MTL) is often achieved by merging datasets before fine-tuning, but the growing availability of fine-tuned models has led to new approaches such as model merging via task arithmetic. A major challenge in this setting is task interference, which worsens as the number of tasks increases. We propose a method that merges models trained on different tasks into a single model, maintaining strong performance across all tasks. Our approach leverages Jensen-Shannon divergence to guide the merging process without requiring additional labelled data, and automatically balances task importance. Unlike existing methods, our approach remains robust as the number of tasks grows and consistently outperforms prior work.

arXiv:2509.09128v1 Announce Type: new Abstract: Conventional machine learning and deep learning models typically rely on correlation-based learning, which often fails to distinguish genuine causal relationships from spurious associations, limiting their robustness, interpretability, and ability to generalize. To overcome these limitations, we introduce a causality-aware deep learning framework that integrates Multivariate Granger Causality (MVGC) and PCMCI+ for causal feature selection within a hybrid neural architecture. Leveraging 43 years (1979-2021) of Arctic Sea Ice Extent (SIE) data and associated ocean-atmospheric variables at daily and monthly resolutions, the proposed method identifies causally influential predictors, prioritizes direct causes of SIE dynamics, reduces unnecessary features, and enhances computational efficiency. Experimental results show that incorporating causal inputs leads to improved prediction accuracy and interpretability across varying lead times. While demonstrated on Arctic SIE forecasting, the framework is broadly applicable to other dynamic, high-dimensional domains, offering a scalable approach that advances both the theoretical foundations and practical performance of causality-informed predictive modeling.

arXiv:2509.08461v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstructured data modalities beyond natural language. In this work, we explore the applications of Vision Language Models (VLMs), specifically a fine-tuned variant of LLaMa 3.2, to the task of identifying neutrino interactions in pixelated detector data from high-energy physics (HEP) experiments. We benchmark this model against a state-of-the-art convolutional neural network (CNN) architecture, similar to those used in the NOvA and DUNE experiments, which have achieved high efficiency and purity in classifying electron and muon neutrino events. Our evaluation considers both the classification performance and interpretability of the model predictions. We find that VLMs can outperform CNNs, while also providing greater flexibility in integrating auxiliary textual or semantic information and offering more interpretable, reasoning-based predictions. This work highlights the potential of VLMs as a general-purpose backbone for physics event classification, due to their high performance, interpretability, and generalizability, which opens new avenues for integrating multimodal reasoning in experimental neutrino physics.

arXiv:2509.09135v1 Announce Type: new Abstract: Existing reinforcement learning (RL) methods struggle with complex dynamical systems that demand interactions at high frequencies or irregular time intervals. Continuous-time RL (CTRL) has emerged as a promising alternative by replacing discrete-time Bellman recursion with differential value functions defined as viscosity solutions of the Hamilton--Jacobi--Bellman (HJB) equation. While CTRL has shown promise, its applications have been largely limited to the single-agent domain. This limitation stems from two key challenges: (i) conventional solution methods for HJB equations suffer from the curse of dimensionality (CoD), making them intractable in high-dimensional systems; and (ii) even with HJB-based learning approaches, accurately approximating centralized value functions in multi-agent settings remains difficult, which in turn destabilizes policy training. In this paper, we propose a CT-MARL framework that uses physics-informed neural networks (PINNs) to approximate HJB-based value functions at scale. To ensure the value is consistent with its differential structure, we align value learning with value-gradient learning by introducing a Value Gradient Iteration (VGI) module that iteratively refines value gradients along trajectories. This improves gradient fidelity, in turn yielding more accurate values and stronger policy learning. We evaluate our method using continuous-time variants of standard benchmarks, including multi-agent particle environment (MPE) and multi-agent MuJoCo. Our results demonstrate that our approach consistently outperforms existing continuous-time RL baselines and scales to complex multi-agent dynamics.

arXiv:2409.00081v2 Announce Type: replace-cross Abstract: Google Scholar is one of the top search engines to access research articles across multiple disciplines for scholarly literature. Google scholar advance search option gives the privilege to extract articles based on phrases, publishers name, authors name, time duration etc. In this work, we collected Google Scholar data (2000-2021) for two different research domains in computer science: Data Mining and Software Engineering. The scholar database resources are powerful for network analysis, data mining, and identify links between authors via authorship network. We examined coauthor-ship network for each domain and studied their network structure. Extensive experiments are performed to analyze publications trend and identifying influential authors and affiliated organizations for each domain. The network analysis shows that the networks features are distinct from one another and exhibit small communities within the influential authors of a particular domain.

arXiv:2509.09146v1 Announce Type: new Abstract: Internet service providers (ISPs) need to connect with other ISPs to provide global connectivity services to their users. To ensure global connectivity, ISPs can either use transit service(s) or establish direct peering relationships between themselves via Internet exchange points (IXPs). Peering offers more room for ISP-specific optimizations and is preferred, but it often involves a lengthy and complex process. Automating peering partner selection can enhance efficiency in the global Internet ecosystem. We explore the use of publicly available data on ISPs to develop a machine learning (ML) model that can predict whether an ISP pair should peer or not. At first, we explore public databases, e.g., PeeringDB, CAIDA, etc., to gather data on ISPs. Then, we evaluate the performance of three broad types of ML models for predicting peering relationships: tree-based, neural network-based, and transformer-based. Among these, we observe that tree-based models achieve the highest accuracy and efficiency in our experiments. The XGBoost model trained with publicly available data showed promising performance, with a 98% accuracy rate in predicting peering partners. In addition, the model demonstrated great resilience to variations in time, space, and missing data. We envision that ISPs can adopt our method to fully automate the peering partner selection process, thus transitioning to a more efficient and optimized Internet ecosystem.