cs.LG · 2026-11-16 · No. 173

Machine Learning, 2026-11-16.

52 new papers in cs.LG. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

52 entries
  1. 01

    Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion

    Daniel Grimm, Kyra Jongman, Renato Cordeiro Ferreira, Giuseppe Cascavilla, Alfredo Cuzzocrea, Willem-Jan Van Den Heuvel

    cs.LG · cs.CR

    Monitoring maritime activities is important for safety and security, particularly for detecting illegal activities, but remains challenging due to the size and complexity of the maritime domain. The Automatic Identification System (AIS) is commonly used for this purpose, despite its known vulnerabilities. In contrast, space-based radio frequency (RF) observations provide an independent source of vessel activity but lack ship identification...

    arxiv.org/abs/2611.18563 · PDF

  2. 02

    WeightBench: Evaluating Language Models as Weight-Space Programmers

    Aayush Marasini, Barsat Khadka, Nick Rahimi

    cs.LG · cs.AI

    Recent work shows that large language models (LLMs) can operate directly on the parameters of other neural networks. They can read what a network was trained to do, fix a network that fails, and write working networks from scratch, all without gradient descent. This capability has been termed Weight-Space Programming (WSP). Exploring this new paradigm systematically requires a robust benchmark. We introduce WEIGHTBENCH, a benchmark that...

    arxiv.org/abs/2611.18553 · PDF

  3. 03

    On numerical issues of divergences between nearly equal distributions

    Brandon Amos

    cs.LG · math.NA · stat.ML

    Barron et al. (2026) recently identified numerical issues in the softmax and soft cross-entropy loss. We show that similar issues are present in standard divergence operations between categorical distributions. This includes the forward and reverse Kullback-Leibler (KL) divergence and generalized Jensen-Shannon divergence (JSD), as well as Monte Carlo KL estimates and entropy. When the distributions are nearly equal, rounding and cancellation...

    arxiv.org/abs/2611.18511 · PDF

  4. 04

    Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy

    Omer Nezih Gerek

    cs.LG · eess.SP

    Classification heads built on conic functions give each class a bounded region of the feature space, and such regions are used to reject samples of unseen classes. We ask whether these regions also keep the features bounded when the head is trained with softmax cross-entropy. For a head whose class scores combine a linear term with a Euclidean norm, we first show that the region of each class is bounded by a quadric of revolution, whose...

    arxiv.org/abs/2611.18507 · PDF

  5. 05

    Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning

    Ahmed Shoyeb Raihan, Md Habibor Rahman, Ashish Nimbarte, Imtiaz Ahmed

    cs.LG

    Accurate prediction of high-entropy alloy (HEA) strength can guide composition and processing decisions; however, obtaining tensile-test data for HEAs can be costly and experimentally demanding. This study proposes Robust Outcome-aware Sequential Experimentation for High-Entropy Alloys (ROSE-HEA), a sample-efficient framework for predicting ultimate tensile strength (UTS) from alloy composition and processing conditions. Its acquisition...

    arxiv.org/abs/2611.18462 · PDF

  6. 06

    Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles

    Wang Ma, Debarun Bhattacharjya, Junkyu Lee, Nhan H Pham, Harsha Kokel, Qiang Ji

    cs.LG · cs.AI

    Reliable use of large language models (LLMs) requires uncertainty estimates that separate ambiguity intrinsic to a prompt from genuine knowledge gaps. Bayesian and deep-ensemble methods deliver this aleatoric/epistemic decomposition in principle, but are computationally prohibitive at LLM scale and require white-box access. Existing black-box methods, in contrast, summarize to a single scalar that cannot make the distinction. We introduce a...

    arxiv.org/abs/2611.18453 · PDF

  7. 07

    PACT: A Decoder-Confidence-Guided Two-Round Receiver for Joint Channel and Phase-Noise Estimation in Sub-THz OFDM

    Ruilin Wang, Xiaodai Dong

    cs.LG · eess.SP

    Frequency-selective fading and oscillator phase noise (PN) jointly impair coded sub-THz OFDM reception. We propose a decoder-confidence-guided two-round receiver combining a {pilot-aware complex transformer} (PACT) estimator, banded linear minimum mean-square error equalization, and neural normalized min-sum decoding. PACT jointly estimates the frequency-domain channel and effective time-domain PN through interacting complex-valued branches....

    arxiv.org/abs/2611.18450 · PDF

  8. 08

    Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs

    Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laurent Navoret, Vignesh Gopakumar

    cs.LG · physics.plasm-ph

    Research in the domain of Physics-Informed Neural Networks applied to PDE modelling has advanced significantly in recent years, providing a wide ecosystem of novel methods. However, one frequent limitation is the inability of PINNs to scale out on High-Performance Computing architectures to address more ambitious challenges, particularly non-linear physics models with turbulent dynamics in large spatial domains. Typical studies restrain...

    arxiv.org/abs/2611.18409 · PDF

  9. 09

    Deep Neural Networks Training Efficiency: Does Grokking Modify its Dynamics?

    Eduardo Cueto-Mendoza, John D. Kelleher

    cs.LG

    We study whether grokking, the delayed emergence of out-of-distribution generalization after apparent overfitting, alters training efficiency in deep neural networks, where efficiency is measured as accuracy per unit energy. Using two canonical settings, modular arithmetic and MNIST, we analyze two neural network models under 16-, 32-, and 64-bit precision and use Orthograd to test whether grokking produces noticeable deviations from the...

    arxiv.org/abs/2611.18396 · PDF

  10. 10

    WeatherDreamer: Learning a World Model from Multimodal Earth Observations

    Kate Duffy, Elise Penn, Tristan Ballard, August Posch, Thomas J. Vandal

    cs.LG · physics.ao-ph

    Machine learning weather models now rival operational global forecasts but still start from analyses produced by separate, expensive data assimilation (DA) systems, which for global models are typically updated every six hours. Observation-to-observation models avoid this dependence, but most omit the recursive filtering cycle that lets DA systems carry a background state through sparse, irregular observations. We introduce WeatherDreamer, a...

    arxiv.org/abs/2611.18393 · PDF

  11. 11

    Where Tree Ensembles Decide: Structural Local Explanation with Decision Predicate Graphs

    Sylvio Barbon Junior, Luca Longo

    cs.LG

    Tree ensembles are among the most accurate models for tabular data, yet the computation behind a single prediction is spread over hundreds of decision rules. Feature attributions and counterfactuals explain such predictions through the influence of features or a change of the input, leaving open which of the thresholds applied by the trees a prediction responds to, while structural explanations compress these rules and lose the trees behind...

    arxiv.org/abs/2611.18382 · PDF

  12. 12

    f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models

    Hoang Tran Vuong, Linh Ngo Van, Dang Nguyen, Thin Nguyen, Phuoc Nguyen, Mehrtash Harandi, Trung Le

    cs.LG · cs.CL

    Anomaly detection in tabular data poses significant challenges due to heterogeneous feature types-mixing numerical, categorical, and textual attributes, which complicate learning meaningful representations of normality. Recent work has applied large language models (LLMs) to this problem by serializing table rows as text sequences, yet these approaches rely on one-shot supervised fine-tuning that offers limited signal to tighten the model's...

    arxiv.org/abs/2611.18370 · PDF

  13. 13

    DECODE: Decomposable Environments for COntrolled Sequential-Decision Evaluation

    Diego Silva Prado, Bruno Caldas de Souza, Tiago Amaral Penteado de Jesus, Ricardo Guimarães Herrmann, Cristiano...

    cs.LG · q-fin.RM · stat.ML

    When a sequential decision system falls short of an optimum, its score does not reveal which modifications would improve its decisions. DECODE is a benchmark for testing such modifications through controlled experiments on planning and available information. Its consumer-credit collections generator provides five partially observed environments that share known dynamics matrices and vary a memory parameter and process noise. The experiments...

    arxiv.org/abs/2611.18367 · PDF

  14. 14

    Emulating physics-based XCO2 retrievals across OCO-2 viewing modes with compact neural networks

    Xianlei San, Chengxing Zhai, Hui Su, Kuai Dai, Shuangchen Du

    cs.LG

    Operational full-physics retrieval of the column-averaged dry-air mole fraction of carbon dioxide from satellite spectra is computationally demanding. We use singular value decomposition to compress spectra from the Orbiting Carbon Observatory-2 separately by band. Compact multilayer perceptrons use the resulting spectral scores, prior information, and viewing geometry to predict the difference between the full-physics retrieval and its...

    arxiv.org/abs/2611.18333 · PDF

  15. 15

    Clean Tickets, Wrong Orders: Catching Silent Errors with a Language Model in Your Browser Tab

    Umar Ahmed, Maxim Dunaev, Mohammad Nour Al Awad, Sergey Ivanov, Ivan Khodnenko

    cs.LG · cs.CL · cs.HC

    A small language model that turns a typed order into structure can fail in two ways. It can print something broken, which any system rejects. Or it can print a clean, well formed order that nobody placed. Our companion work calls the second kind a silent error, and it is the dangerous one. We present a web demo in which a fine-tuned 0.8B parameter model runs entirely inside the visitor's browser tab, through llama.cpp compiled to WebAssembly....

    arxiv.org/abs/2611.18284 · PDF

  16. 16

    Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering

    Nima Eshraghi, Lovedeep Gondara, Sagarika Suresh, Xiaotong Xu, Jithin Pradeep, Fanny Chevalier

    cs.LG · cs.AI

    Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning. Yet, standard methods apply the steering signal at every generated token, displacing representations from the distribution the model was trained on and eroding generation quality. We show that \emph{when} along a generation the intervention is applied is a decisive axis of control. We cast steering as a...

    arxiv.org/abs/2611.18274 · PDF

  17. 17

    ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization

    Pei Tang, Songtao Lu

    cs.LG · cs.AI · math.OC

    Learning across multiple inherently conflicting objectives requires selecting desirable trade-offs from the Pareto set. In this work, we study preference-guided multi-objective optimization, where a predefined preference function is minimized over the weak Pareto set of multiple nonconvex objectives. Leveraging a merit function that vanishes on the weak Pareto set, we propose a penalty-based min-max-min formulation, termed the M$^3$ problem,...

    arxiv.org/abs/2611.18252 · PDF

  18. 18

    Neural Classifiers as Error-Correcting Codes

    Sergey Salishev, Anton Makarov, Oleg Granichin, Renata Avros, Zeev Volkovich

    cs.LG · cs.IT

    A unified framework is proposed that characterizes supervised deep classification as the decoding of error-correcting codes in the Shannon sense. Cross-entropy optimization is shown to align softmax classifiers with maximum-likelihood decoding, where logits map to Hamming distances to class-specific codewords. This correspondence explains the emergence of standard divergence objectives (e.g., Kullback-Leibler, Jeffreys) and provides a...

    arxiv.org/abs/2611.18239 · PDF

  19. 19

    Small Is Not Dead: Distance-Aware Cluster Revival for e-means

    Eyal Weiss

    cs.LG · stat.ML

    e-means (Bessa et al., 2026) is a recent mini-batch k-means algorithm, now part of the FAISS library, that reaches the error of Lloyd's algorithm about an order of magnitude faster on large embedding datasets. Every five mini-batches, it removes every cluster whose running point count falls below a tenth of the average and reuses its centre to split a large cluster. In the authors' ablation, removing this mechanism, called dead-cluster...

    arxiv.org/abs/2611.18238 · PDF

  20. 20

    NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery

    Ze Guo, Mingyue Cheng, Xiaoyu Tao, Shuo Yu, Shangtong Ye

    cs.LG

    Developing effective forecasting models for diverse time-series domains requires substantial expert knowledge, evidence from scientific literature on the web, and iterative experimentation. However, translating this knowledge and research experience into model designs requires preserving source context and testing applicability under task-specific assumptions. In this paper, we propose NeoResearch, a literature- and experience-guided...

    arxiv.org/abs/2611.18235 · PDF

  21. 21

    T2ST: Data-Efficient Spatio-Temporal Foundation Models via Temporal Data and Knowledge Transfer

    Yue Xu, Kaiyun Wei, Wenying Duan, Zichen Xu, Shuai Ma, Xiaoxi He

    cs.LG · cs.AI

    Spatio-temporal foundation models (STFMs) require large-scale training corpora, yet synchronized observations and spatial metadata are costly to acquire and curate, limiting the availability of suitable data. By contrast, time-series data are abundant and easier to collect. Since observations at each location form a time series, this motivates a natural question: can abundant time-series data enhance STFMs when spatio-temporal observations...

    arxiv.org/abs/2611.18199 · PDF

  22. 22

    MarathonTS: a benchmark of long synthetic time series from window assembly and long-series generators

    Ilyas Varshavskiy, Sergey Shulgin, Shuhrat Khalilbekov, Bonu Boboeva, Azizjon Azimi

    cs.LG

    Many applications of synthetic time series require a series that is much longer than the windows on which a generative model is trained. Such a series can be assembled from a pool of short generated windows, which requires deciding which windows are taken, in what order, and how their seams are processed, or it can be produced directly by a long-series generator. This study presents MarathonTS, to our knowledge the first open benchmark that...

    arxiv.org/abs/2611.18190 · PDF

  23. 23

    On the Limits of Sufficient Explanations

    Klaus Weinbauer, Peter F. Stadler, Thomas Gärtner, Sagar Malhotra

    cs.LG

    We formally characterize the conditions under which sufficient explanations exist for classifiers on structured data such as graphs and strings. We focus on post-hoc explainers that select parts of the input as sufficient explanations. An explanation is sufficient if the selected part alone ensures the predicted label. Sufficient explanations have been widely adopted across data modalities, including graphs, strings, and images. However, a...

    arxiv.org/abs/2611.18163 · PDF

  24. 24

    Which Model, For Which Variable? Per-Variable Forecast Combination in Sparse ICU Time Series

    Marius Fracarolli, Stefan Riezler

    cs.LG

    Clinical forecasting papers typically report a single best architecture. We show that on multivariate ICU physiology this question conceals variable-specific differences: no architecture is best on every variable, and which model wins changes from variable to variable. Across five ICU databases (MIMIC-III, MIMIC-IV, eICU, HiRID, and UMM (University Medicine Mannheim), a German single-center ICU) we forecast 94 channels over a 24-hour horizon...

    arxiv.org/abs/2611.18149 · PDF

  25. 25

    STAMP: Manufacturing-Informed Generative Design and Shape Optimization of Sheet Panels

    Jihoon Kim, Jun Hyeok Song, Wonho Ha, Namwoo Kang

    cs.LG

    Generative design of formed sheet panels must preserve geometric manufacturing conditions while exploring layouts and improving performance. STAMP embeds these conditions directly in the shape representation. Each panel is described by its material layout and a reference surface with one height at each occupied position in a plane perpendicular to the drawing direction. Nominal thickness is prescribed along the normal. The representation...

    arxiv.org/abs/2611.18144 · PDF

  26. 26

    When Copying Is Hard to Beat: A Negative Result in Clinical Assessment Forecasting

    Marius Fracarolli, Stefan Riezler

    cs.LG

    We report a negative result in next-day clinical assessment forecasting: the evaluated models show no consistent advantage over strong persistence-based baselines. Clinicians can view the previous day's questionnaire answers, a plausible source of documentation persistence. Predicting 45 items on 29,715 ICU day-pairs with patient-disjoint splits, a physiology-informed gated model improves item-macro-F1 over a one-line clinical rule by +0.0019...

    arxiv.org/abs/2611.18142 · PDF

  27. 27

    Efficient Poincaré Convolutions through Patch-Statistics Factorization

    Lukáš Jochymek, Markéta Vašinková, Petr Gajdoš

    cs.LG · cs.NE

    Published implementations of the Poincaré convolution in Hyperbolic Neural Networks++ (HNN++) map every overlapping image patch to the Poincaré ball before evaluating its score. We show that the clipped score depends on each patch only through two statistics, its squared norm and its inner products with the filters, which a native convolution and a single-channel box filter compute directly. The factorized layer therefore evaluates the...

    arxiv.org/abs/2611.18125 · PDF

  28. 28

    Deep Latents, Long Memory: Latent persistence explains temporal correlations in transformer activations

    Francesco Cagnetta, Santiago Acevedo

    cs.LG · cs.CL

    The hidden layers of Large Language Models (LLMs) are believed to encode representations of the data whose abstraction increases with depth. However, in the absence of an operational notion of abstraction, this statement is hard to test quantitatively. Here, we propose an alternative view, building on the principle that the correlations of a sequence reflect the structure of the process that generated it. We define the autocorrelation...

    arxiv.org/abs/2611.18089 · PDF

  29. 29

    Learning nonlinear interactions and cross-feature couplings with product-unit residual networks

    Ziyuan Li, Uwe Jaekel, Babette Dellen

    cs.LG · cs.NE

    Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability. We investigate complex-valued product-unit residual networks (CV-PURe) that integrate multiplicative product units with residual connections to explicitly model cross-feature couplings...

    arxiv.org/abs/2611.18074 · PDF

  30. 30

    Enrichment-Oriented Virtual Screening of Perovskite Solar Cells through Reinforcement Learning

    Yezeyuan Zheng, Ziyang Hu, Maojun Sun. Ruijian Han, Jian Huang, Guanhua Chen, Jie Liu

    cs.LG

    Experimental optimization of perovskite solar cells is constrained by combinatorial diversity in absorber compositions, device layers, and processing, which makes virtual screening attractive for prioritizing recipes before fabrication. We develop a surrogate-guided reinforcement-learning framework that casts recipe generation as virtual screening, enriching candidate shortlists near high-performing experimental neighbors. A frozen Tabular...

    arxiv.org/abs/2611.18043 · PDF

  31. 31

    RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime

    Zexin Li, Xinwei Gao, Arvind Easwaran

    cs.LG · cs.AI

    On-device reinforcement learning runs a periodic actor and a learner on one embedded GPU shared with other workloads. Because the learner produces the actor's weights, existing designs stall the actor or let its policy drift. We present RL$^{\mathrm{RT}}$, an on-device runtime that makes this coupling a tunable parameter: a refresh bound limits actor releases between refreshes, and a GPU permit with slack-aware admission prioritises the actor...

    arxiv.org/abs/2611.18035 · PDF

  32. 32

    Conflict, Feasibility, Faithfulness, Displacement: Four Quantities That Come Apart in Federated Dual-Cone Aggregation

    Grzegorz Gwardys, Karol Wojciechowski, Mateusz Gwardys, Bartosz {Ś}widerski

    cs.LG

    FedFV, FedGH and FedMGDA+ aggregate client updates with multi-objective gradient aggregators to remove conflict between them. We examine this rationale with UPGrad, which increases no client's loss to first order, in a comparison that changes only the direction of FedAvg's update. Four quantities the rationale treats as one -- conflict between client updates, feasibility of their weighted mean, faithfulness of the transmitted updates to the...

    arxiv.org/abs/2611.18014 · PDF

  33. 33

    Sample-Efficient Control of Magnetoconvective Flows via Differentiable Simulation

    Jannis Becktepe, Dmitry Krasnov, Nils Thuerey, Jörg Schumacher, Sebastian Peitz

    cs.LG · physics.flu-dyn

    Magnetohydrodynamic (MHD) fluid flows are central to demanding engineering applications, most prominently fusion blanket cooling, where flow control is a promising tool to optimize key properties such as heat transfer. While active flow control (AFC) has recently advanced through machine learning, its application to MHD flows remains largely unexplored. In this work, we present $φ$-PICT, a novel differentiable GPU-accelerated MHD solver...

    arxiv.org/abs/2611.18008 · PDF

  34. 34

    RiverScan: Learning to Accumulate on River Networks

    He Zhu, Zhiyi Gao, Youhuan Yang, Han Quan, Ming Li

    cs.LG

    Accurate runoff prediction across large river basins requires models to capture heterogeneous local hydrological responses and their accumulation downstream. River-network connectivity provides a natural structure for this task, but using it effectively requires learning how to combine contributions from subcatchments of different sizes. We frame this challenge as learning to accumulate and introduce RiverScan, a spatial operator based on...

    arxiv.org/abs/2611.18005 · PDF

  35. 35

    When Does Oversampling Help? A Decision Framework for Imbalanced Data Streams Under Label Delay and Concept Drift

    Ahmed Awad, Anirudh Sengar

    cs.LG

    For imbalanced data streams with delayed labels, is it worth adding a streaming oversampler, or does continuous re-evaluation of earlier predictions already recover the cost of the delay? We address this through an extensive experimental comparison of streaming oversampling and continuous re-evaluation under joint class imbalance, concept drift, and label delay. Streaming oversamplers are typically evaluated under the test-then-train...

    arxiv.org/abs/2611.17981 · PDF

  36. 36

    Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models

    Dongwoo Kim

    cs.LG

    Denoising generative models predict clean data ($x$), noise ($ε$), or velocity ($v$), while training losses can be measured in any of these spaces. Although the resulting nine combinations are algebraically related, they can yield substantially different denoising accuracy and sample quality. We disentangle the effects of prediction and loss spaces. For a fixed prediction target, we show that changing the loss space is exactly equivalent to...

    arxiv.org/abs/2611.17967 · PDF

  37. 37

    DeltaVisionX: A Low-Cost Vision-Guided Automation System Using YOLOv11 and PLC-Based Actuation

    Lara Sobh, Marc Nahhas, Francisco Katach El Halabi, Michel Owayjan, Fadi Elias Sleiman

    cs.LG

    This paper presents DeltaVisionX, a low-cost industrial automation system that integrates real-time computer vision with PLC-based actuation for object classification and sorting. The system uses the YOLOv11 (You Only Look Once) deep learning model to detect objects on an operating conveyor belt and communicates detection results to a Delta DVP-SE PLC, which actuates pneumatic pistons for sorting. A custom dataset was created, labeled, and...

    arxiv.org/abs/2611.17959 · PDF

  38. 38

    Reasoning Models Confabulate to Defend Injected Beliefs About Their Own Requests

    Yang Ou

    cs.LG

    Chain-of-thought (CoT) monitoring and self-report are proposed as levers for AI oversight, on the assumption that a model's account of what it is doing is anchored to what it was asked. We show this anchor can be cut. An activation edit invisible in the prompt text, the injected forming-trace of an off-topic concept, overwrites a reasoning model's belief about its own request: across six models spanning scale, architecture, and recipe, the...

    arxiv.org/abs/2611.17958 · PDF

  39. 39

    Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification

    Baran Can Gül, Ali Gülümser, Nasser Jazdi, Michael Weyrich

    cs.LG

    Federated learning (FL) under differential privacy (DP) is typically evaluated on large client cohorts, where subsampling and cross-client averaging amplify privacy and smooth injected noise. Personal biosignal applications such as wearable EEG instead involve small federations of a handful of subjects, a regime whose interaction with formal client-level DP is largely uncharacterized. We study differentially private federated...

    arxiv.org/abs/2611.17944 · PDF

  40. 40

    TIDE: Reclaiming Lost Performance In On-Policy Reinforcement Learning

    Mathew Jacob, Morgan Borjigin-Wang, Kan Zhu, Po Hao Chen, Yi Pan, Andy Ruan, Nayani Modugula, Ethan Lavi, Luis Ceze,...

    cs.LG · cs.DC · cs.PF

    Synchronous, colocated RL post-training of large language models (LLMs) today suffers from severe under-utilization due to long-tail rollouts. Inference engines fall idle waiting for long-tail rollouts or decode at low, inefficient batch sizes. To address this, we present TIDE, an RL training system that preserves on-policy training semantics while recovering resource utilization. TIDE does so by two complementary techniques: (1) dynamically...

    arxiv.org/abs/2611.17924 · PDF

  41. 41

    Quantum Graph Neural Networks: Architectures, Trainability, and Applications

    Zeinab Sharifi, Hossein Shirazi

    cs.LG

    Quantum graph neural networks (QGNNs) apply parametrized quantum circuits to graph-structured data, with the aim of overcoming limits of classical graph neural networks in scalability, expressivity, and long-range information flow. Since the first Hamiltonian-based model in 2019, the field has produced many architectures, applications, and claims, but the evidence behind them has not been assessed systematically. This survey introduces a...

    arxiv.org/abs/2611.17886 · PDF

  42. 42

    From Local Prediction Error to Final Outputs: A Theory of Expert Sharing in Multi-Step Reasoning

    Tiantong Wang, Zhiren Gong, Yixin Wang, Tiantong Wu, Wei Yang Bryan Lim

    cs.LG · cs.AI

    Mixture-of-experts (MoE) models can share experts across layers or computational steps, pooling training information from different contexts. This can reduce local prediction error, but multi-step systems are ultimately evaluated by their final outputs. We study when these local gains survive composition. In specified linear regression models, we derive exact sharing and merging criteria by balancing variance savings against bias from sharing...

    arxiv.org/abs/2611.17879 · PDF

  43. 43

    Delayed Effects of Temporary Weight Decay in Muon Pretraining

    Md Rifat Arefin, Ravid Shwartz-Ziv, Ernie Chang, Chinnadhurai Sankar, Rylan Conway, Aristide Baratin, Irina Rish,...

    cs.LG · cs.CL

    A temporary optimization intervention can increase validation loss when it ends yet reduce it at the final training budget. We demonstrate this with temporary weight decay in Muon-trained decoder-only Transformers with 162M, 405M, 1.4B, and 3.4B parameters. For models up to 1.4B parameters, moving a fixed-duration decay window from early to late training reverses its final effect. At 162M, changing window duration alters final loss even at...

    arxiv.org/abs/2611.17876 · PDF

  44. 44

    Protection-Oriented Assessment of Machine Learning-Based Fault Detection in Power Systems

    Julian Oelhaf, Georg Kordowich, Changhun Kim, Christian Bergler, Andreas Maier, Johann Jäger, Siming Bayer

    cs.LG · eess.SP

    Machine learning (ML)-based fault detectors are increasingly proposed for power system protection, yet aggregate metrics can obscure the consequences of false and missed trips. We present a protection-oriented assessment of three ML detectors and a sequence-current reference on PROTECT-90, comprising 9,022 simulated fault episodes on a 90 kV double-circuit line. The assessment combines five window conditions, causal window-end labelling,...

    arxiv.org/abs/2611.17872 · PDF

  45. 45

    Process Mining-Enabled Federated Anomaly Detection for the Industrial IoT

    Francesco Vitale, Salvatore Bramante, Francesco Flammini, Hangli Ge

    cs.LG

    While federated anomaly detection enables the integration of local data insights across diverse nodes to reduce false positives, it inherently struggles with non-IID data. In practice, industrial IoT plants often operate under varying conditions and experience diverse environmental phenomena, resulting in significant heterogeneity in the monitored time series. In such settings, standard federated learning approaches fail to perform nuanced...

    arxiv.org/abs/2611.17869 · PDF

  46. 46

    Disentangling Forgetting from Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection

    Xiuyuan Wang, Weiming Liu, Zongxin Yang, Fan Wang, Liemiao Jin, Rubin Qin, Wei Chen, Bin Shi, Chaochao Chen, Xiaolin Zheng

    cs.LG

    Large Language Models (LLMs) pose significant security risks by retaining private or hazardous information, creating an urgent need for unlearning techniques that excise specific knowledge without compromising general utility. However, prevailing fine-tuning-based unlearning methods struggle to achieve this balance, often suffering from computational inefficiency and unintended utility degradation due to the entangled nature of knowledge...

    arxiv.org/abs/2611.17864 · PDF

  47. 47

    Fuse-All MoE Inference Kernel with Load Balancing on TPUs

    Rupeng Liu, Bangsheng Tang, Zongwei Zhou, Chengji Yao, Yejin Lee

    cs.LG

    Mixture-of-Experts (MoE) architectures activate only a subset of experts for each token, allowing large language models (LLMs) to scale parameter capacity without a proportional increase in computation per token. However, intermediate data movement and uneven expert loads limit the efficiency of MoE inference on TPUs. To address these bottlenecks, we introduce Fuse-All MoE, a TPU kernel design that jointly optimizes expert computation, output...

    arxiv.org/abs/2611.17857 · PDF

  48. 48

    Electrocardiographic Imaging via Posterior Sampling under Operator Discrepancy

    Ricarda Buttmann, Andreas M. Lehrmann

    cs.LG

    Electrocardiographic imaging (ECGI) reconstructs heart-surface potentials from body-surface potentials, an ill-posed inverse problem. Diffusion posterior samplers combine a learned prior with an explicit forward operator that they assume to be accurate. In ECGI this operator is only an estimate, because the body changes with respiration and posture, and body composition such as subcutaneous fat is rarely known for an individual patient. The...

    arxiv.org/abs/2611.17851 · PDF

  49. 49

    Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing

    Amirul Islam Saimon, Zhenyu, Kong

    cs.LG

    In additive manufacturing (AM), each change in part geometry requires a new thermal simulation, which makes design evaluation over many candidates costly. Geometry-aware models reduce this cost by predicting thermal fields on unseen parts with a single learned model, but they assume that diverse geometries are available centrally. This assumption is restrictive when each manufacturing site holds only a limited set of proprietary part designs...

    arxiv.org/abs/2611.17794 · PDF

  50. 50

    Direction or Magnitude? Learning Scalars over Task-Calibrated Directions

    Ziqing Wen, Xiaohui Song, Jiahuan Wang, Ping Luo, Junlin Zeng, Dongsheng Li, Kele Xu, Tao Sun

    cs.LG

    Parameter-efficient fine-tuning (PEFT) aims to preserve adaptation quality while reducing training costs. We propose SCALAR, which achieves performance comparable to LoRA with substantially fewer trainable parameters, lower peak training memory, and higher throughput. SCALAR constructs a fixed input basis from task activations and assigns a random output dictionary to each input direction. Fine-tuning learns only layer-specific scalar...

    arxiv.org/abs/2611.17784 · PDF

  51. 51

    Antidistillation is Cheap: Lightweight Distillation-Resistance via Stylistic Corruption

    Anh Tu Ngo, Anupam Chattopadhyay

    cs.LG

    Knowledge distillation (KD) is a highly effective paradigm for transferring capabilities from large language models (LLMs) to smaller, more specialized student models. In commercial deployment where frontier models are restricted behind black-box APIs, sequence-level distillation remains a potent vector for competitors to clone proprietary capabilities at a fraction of the development cost. Existing defenses mostly rely on surrogate models to...

    arxiv.org/abs/2611.17772 · PDF

  52. 52

    Complex Schrödinger Bridges

    Dong-Sig Han, Tolga Birdal

    cs.LG · stat.ML

    Diffusion bridges have emerged as versatile frameworks for facilitating transformations between arbitrary data distributions. However, these approaches are hindered by an immense optimization space and its underlying high-order structures. This paper explores a variant of diffusion bridges for solving real-world problems in complex vector spaces governed by scaling and rotation laws, such as Hamiltonian structures. To address this, we...

    arxiv.org/abs/2611.17746 · PDF

This edition is part of The Daily Abstract — cs.LG archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.