cs.LG · 2026-09-17 · No. 116

Machine Learning, 2026-09-17.

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

01 — The papers

56 entries
  1. 01

    Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

    Pranaya Jajoo

    cs.LG

    Can a logged dataset visit every hidden state frequently and still be exponentially uninformative about a target policy's value? We show that it can when the logger depends on history. For every horizon $H \ge 3$, we construct two POMDPs with at most two latent states per stage, three actions, and a common logger with three memory states. Action coverage, belief coverage, and two behavior-marginal outcome-revealing conditions all have...

    arxiv.org/abs/2609.19135 · PDF

  2. 02

    How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents

    Zixi Chen, Akshay Vegesna, Samip Dahal, Andrew Gordon Wilson

    cs.LG

    Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to exponential improvements in performance with increases in computation. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth,...

    arxiv.org/abs/2609.19107 · PDF

  3. 03

    Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory

    Michael M. Craig, Riley J. Hickman, Yingshan Ma, Rémi Piché-Taillefer, Christine Allen, Pauric Bannigan

    cs.LG

    Self-emulsifying drug delivery systems (SEDDS) can improve the oral bioavailability of poorly soluble drugs, but identifying high-performing formulations remains experimentally intensive. We present Andromeda 2, an agentic system that reasons over structured in-house experimental evidence and invokes computational and experimental tools to design and execute successive formulation batches. Using a miniaturized automated laboratory at a...

    arxiv.org/abs/2609.19099 · PDF

  4. 04

    Probabilistic Linear Explanations

    Frederic Koriche, Jean-Marie Lagniez, Chi Tran

    cs.LG · cs.AI

    Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human cognitive limits by involving too many features, while probabilistic relaxations have remained largely limited to categorical classification. We present a unified framework for probabilistic explainability based on sparse, anchored linear models, applicable to both binary classification and...

    arxiv.org/abs/2609.19077 · PDF

  5. 05

    Double descent is the principle of least action

    Congzhou M Sha

    cs.LG · cs.AI · math.ST · physics.comp-ph · physics.data-an

    The test error of a model plotted against its number of parameters $d$ falls, peaks when the model can just fit the training data, and falls again, exhibiting the double descent phenomenon. We explain the phenomenon with statistical mechanics. The training trajectory of a stochastic gradient-based method is a particle wandering over the energy landscape of the training loss at an induced temperature $T$, and a run that has equilibrated visits...

    arxiv.org/abs/2609.19076 · PDF

  6. 06

    RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control

    Bernd Frauenknecht, Emma Cramer, Artur Eisele, Paul Kruse, Lukas Kesper, Jonas Hertrampf, Ramil Sabirov, Jyotirmaya...

    cs.LG · cs.AI

    Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interactions between different objects that play out over several cycles. Such dynamics are often best explained with an easily accessible implementation. We present RLLBC-Lib, a carefully crafted code library with the goal of lowering the entry barrier for students and other learners of RL in the...

    arxiv.org/abs/2609.19074 · PDF

  7. 07

    Higher-order pruning of experts in mixture-of-experts language models

    Alex M. Tseng, Prannay Kaul, Luca Zancato, Wei Xia, Stefano Soatto

    cs.LG · cs.AI

    Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most direct approach for reducing this parameter count, yet existing methods make pruning decisions for each expert independently, and assume experts' contributions are purely additive. In reality, expert usage in MoEs is inherently cooperative. We derive HOPE (Higher-Order Pruning of Experts), a...

    arxiv.org/abs/2609.18916 · PDF

  8. 08

    Preventing Model Collapse: A Fisher-Rao Perspective on the Dynamics of Training with Synthetic Data

    Matteo Marchi, João Pedro Silvestre, Bahman Gharesifard, Paulo Tabuada

    cs.LG · eess.SY

    Large Language Models (LLMs) are now routinely trained using synthetic data, since high-quality human data has been exhausted by the ever increasing needs of larger and larger models. However, recursive training on synthetic data frequently induces model collapse, a degenerative feedback loop where models progressively forget the true underlying data distribution. Training on a mixture of synthetic and fresh human data is a logical...

    arxiv.org/abs/2609.18878 · PDF

  9. 09

    Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes

    Yisheng Lu, John Riris, Jie Song, Yao Fu, Jie Chen

    cs.LG · cond-mat.mtrl-sci · cs.CE

    Reliable prediction of crystallographic texture in laser powder bed fusion is critical for linking process conditions with anisotropic response and for qualification. However, black-box models may fail under shift and cannot distinguish weak data support from loss of physical validity. This study develops a two-stage physics-based model for <001> || BD (build direction) texture in Inconel 718. Stage 1 maps process variables to melting mode...

    arxiv.org/abs/2609.18863 · PDF

  10. 10

    Interpretable Multi-Instance Learning Enables Early Prediction of Key Molecular Alterations from Routine Flow Cytometry in Acute Myeloid Leukemia

    Jonathan Legrand, Aguirre Mimoun, Baudouin Denis de Senneville, Audrey Bidet, Pierre-Yves Dumas, Christèle Etchegaray

    cs.LG

    Background: Molecular testing for NPM1 and FLT3-ITD mutations guides critical early treatment decisions in acute myeloid leukemia (AML), but results can take weeks, long after these decisions must be made. Flow cytometry, already performed within hours of admission as part of routine care, may carry enough signal to predict these mutations directly, without added cost or delay. Methods: We developed an interpretable multi-instance learning...

    arxiv.org/abs/2609.18825 · PDF

  11. 11

    WaveTLM: Reliable Time-Series Language Modeling through Task Compilation

    Jiahui Chen, Bingke Zhu, Hongyu Pan, Yingying Chen

    cs.LG

    Time-series language models provide a shared natural-language interface across temporal tasks, but plausible text does not guarantee reliable task outputs. Responses may appear reasonable while hallucinating the required object: numerical sequences can violate shape, scale, channel order, or temporal alignment, and textual decisions can fall outside the legal label space. We formulate reliable time-series language modeling, separating...

    arxiv.org/abs/2609.18812 · PDF

  12. 12

    A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds

    Yury Kolomeytsev

    cs.LG · cs.RO · math.OC

    We establish convergence bounds for deep $V$-learning with horizon $H$. The algorithm fits a scalar value function to targets from executed transitions and selects actions using a predictive model and the value function. For current observed-successor targets with fresh true-kernel outcomes, the conditional mean is $\mathcal{T}^βV$, which averages over behavior-policy actions. The Bellman optimality update is $\mathcal{T} V$. We decompose the...

    arxiv.org/abs/2609.18782 · PDF

  13. 13

    When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows

    Gabriel Bénédict, Melanie Buechler, Gerard Riera-Solà, Chloé de Ancos, Yves Gaetan Nana Teukam, Moritz Freidank

    cs.LG · stat.ML

    Antibody lead optimization calls for a small, bounded set of edits to an existing candidate: substitutions, but also insertions and deletions. Edit-based generative models are the only ones that allocate such an edit budget without fixing the edit positions, the edit count, or the output length in advance. However, the existing approaches Edit Flows and EvoFlows did not release code or complete training specifications. Here, we show that both...

    arxiv.org/abs/2609.18745 · PDF

  14. 14

    Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

    Yizhuo Li, Jianhao Yan, Yun Luo, Zhi Wang, Futing Wang, Rong-Xi Tan, Kanghui Tian, Ganqu Cui, Ning Ding, Peilin...

    cs.LG · cs.AI

    In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo continuations, change sharply across intermediate states while critic predictions remain comparatively flat. We further...

    arxiv.org/abs/2609.18708 · PDF

  15. 15

    Revisiting Distributed Sign-Based Variance Reduction

    Wei Jiang, Zechao Li, Lijun Zhang

    cs.LG · math.OC · stat.ML

    Sign-based methods reduce communication costs in distributed environments, but aggregating local signs can introduce bias when data are heterogeneous. As a result, existing sign-based variance reduction methods fail to obtain the optimal convergence rates. In this paper, we solve this problem and obtain optimal rates for both nonconvex stochastic and finite-sum optimization. We first give a counterexample showing that majority voting can fail...

    arxiv.org/abs/2609.18656 · PDF

  16. 16

    Learning to Program Adaptive Non-Local Observables for Machine Learning

    Yu-Ting Lee, Samuel Yen-Chi Chen, Huan-Hsin Tseng

    cs.LG · quant-ph

    Quantum neural networks (QNNs) are typically built from variational quantum circuits (VQCs), which are limited by local measurements. Adaptive non-local observables (ANO) address this by jointly optimizing circuit parameters and multi-qubit measurements. However, existing ANO-based VQCs learn only a single static observable that remains invariant across all inputs. We propose QFWP-ANO, a novel architecture which employs a classical...

    arxiv.org/abs/2609.18655 · PDF

  17. 17

    CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning

    Naimur Rahman Chowdhury, Shatabdi Sen Prapti, Md. Salehin Seyam, Limon Bin Hossain

    cs.LG · cs.AI

    Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs operate in a decentralized network of local centers that face uncertain local demand and supply dynamics, resulting in inconsistent avail- ability of local services. Redistribution of supplies among these local centers reduces these imbalances, but the centers often make...

    arxiv.org/abs/2609.18639 · PDF

  18. 18

    How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction

    Tetsuji Kuboyama

    cs.LG · stat.ML

    Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differently. We quantify this requirement for the area under the generalized risk-coverage curve (AUGRC). A prelabel lower bound rules out insufficient budgets. With all labels known, a covering linear program bounds the minimum number of labels sufficient to fix the winner (the certificate size) within...

    arxiv.org/abs/2609.18622 · PDF

  19. 19

    Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence

    Sebastian Gerstner, Hilal AlQuabeh, Kentaro Inui, Hinrich Schütze

    cs.LG · cs.CL

    We analyze the learned input-output behavior of GLU-based neurons in large language models (LLMs). We propose a simple analysis method: For each neuron, we compute the cosine similarities between its input (reading) and output (writing) weight vectors. In this scheme, a strong negative cosine similarity indicates the neuron weakens the direction it detects in the residual stream, so we call this a weakening neuron. This allows us to gain a...

    arxiv.org/abs/2609.18612 · PDF

  20. 20

    A Geometric Theory of Decision Boundaries in Structured Markov Decision Processes

    Fredy Pokou

    cs.LG · math.OC

    Classical dynamic programming represents optimal sequential decisions through value functions and policies. While this functional representation is natural for computing optimal decisions, it does not directly identify the mathematical object governing policy reconstruction, representation complexity, or oracle-query complexity once an optimal policy is fixed. This paper addresses this question by developing a geometric theory of structured...

    arxiv.org/abs/2609.18610 · PDF

  21. 21

    Online Robust Reinforcement Learning Through Monte-Carlo Planning

    Tuan Dam, Kishan Panaganti, Brahim Driss, Adam Wierman

    cs.LG · cs.AI

    Monte Carlo Tree Search (MCTS) is a powerful framework for solving complex decision-making problems, yet it often relies on the assumption that the simulator and the real-world dynamics are identical. Although this assumption helps achieve the success of MCTS in games like Chess, Go, and Shogi, the real-world scenarios incur ambiguity due to their modeling mismatches in low-fidelity simulators. In this work, we present a new robust variant of...

    arxiv.org/abs/2609.18599 · PDF

  22. 22

    ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networks

    Rupesh Raj Karn, Johann Knechtel, Ozgur Sinanoglu

    cs.LG · cs.NE

    Logic resynthesis preserves circuit functionality while changing gate vocabulary, topology, and structural statistics, creating domain shift for circuit graph neural networks (GNNs) without changing task labels. To study this setting, we introduce ReDIL-GNN, a resynthesis domain-incremental learning framework that adapts a fixed prediction or representation head as new synthesis styles arrive and evaluates retention on all previously observed...

    arxiv.org/abs/2609.18595 · PDF

  23. 23

    Peak-Aware Short-Term Load Forecasting Across Distribution Grid Aggregation Levels

    Souhardya Chattopadhyay, Julian Oelhaf, Antonia Schoening, Jessica Deuschel, Bitan Bhattacharyya, Christian Bergler,...

    cs.LG

    For distribution system operators, short-term load forecasting (STLF) supports congestion management, voltage control, and asset protection. Most existing approaches focus on overall accuracy across all time steps and neglect performance during high-demand (HD) periods, where larger forecast errors can increase the risk of congestion and voltage violations. In this paper, we study peak-aware STLF across three operator-relevant distribution...

    arxiv.org/abs/2609.18588 · PDF

  24. 24

    Label-free steering: Compressing test-time reinforcement learning into bias-only subspaces

    Naveen Vakada, Mingyuan Li, Shaoxiong Ji

    cs.LG · cs.AI

    Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters. This raises a natural question: can effective test-time adaptation emerge when both the reward signal and the optimization space are severely restricted? We answer this question with label-free bias-only TTRL, which uses majority-vote...

    arxiv.org/abs/2609.18587 · PDF

  25. 25

    Accurate Trace Estimation with Fewer Random Bits via Recursive TensorSketch

    Mohammad Azhar Khan, Rameshwar Pratap, Amit Sharma

    cs.LG · cs.DS

    We consider the problem of estimating the trace of an implicit matrix $\mathbf{A} \in \mathbb{R}^{d^p\times d^p}$ that can only be accessed through matrix-vector products queries. The \textit{Hutchinson trace estimator}% ~\cite{Girard1987algorithme, article-hutchinson} is a classical sketching method for this problem. Their estimator, $H_{m}(\mathbf{A}) = \frac{1}{m} \sum_{i=1}^{m} {\mathbf{z}^{(i)}}^T \mathbf{A} \mathbf{z}^{(i)}, \quad...

    arxiv.org/abs/2609.18577 · PDF

  26. 26

    The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations

    Giorgio F. Gilestro

    cs.LG · cs.NE · q-bio.PE

    Some aspects of AI development resemble a population process in which models are specialised, retrained on the output of peers, or combined by averaging weights. These practices lead to generations of models, in the biological sense studied by population genetics. Here, I develop this parallelism and interpret multigenerational model populations in terms of sexual and asexual reproduction, formally recombining the two fields. I test these...

    arxiv.org/abs/2609.18560 · PDF

  27. 27

    Interpretable Patch-Based Deep Learning for Wildfire Spread Prediction from Ensemble Simulations

    Marcin Lawenda, Aleksandra Krasicka, David Caballero, Luis Torres, Łukasz Szustak

    cs.LG · cs.AI

    Wildfire spread is traditionally predicted using physics-based simulators, which are physically interpretable but whose cost increases with each additional ensemble member. We ask how well deep learning surrogates can reproduce these simulations at a fraction of this cost, training them on 10,584 fire spread simulations at 2m resolution for the Rectoret region in Catalonia, Spain. Four architectures are compared: a patch-based U-Net, a...

    arxiv.org/abs/2609.18555 · PDF

  28. 28

    Revisiting the Objective of Echo Chamber Detection

    Abylaikhan Bexeit, Kushani Perera, Shanika Karunasekera, Jean Honorio

    cs.LG

    In this paper, we study the detection of an echo chamber in a social network, i.e., the identification of a set of nodes that agree on a topic, while disagreeing with the rest of nodes. We argue that this problem is different from other social network analysis problems such as community detection, and from other graph problems such as maximum graph cut and maximum clique. To the best of our knowledge, we are the first to formalize the...

    arxiv.org/abs/2609.18545 · PDF

  29. 29

    Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders

    Weijian Yu, Jean Honorio

    cs.LG · stat.ML

    Causal discovery aims to recover causal relationships from observed data. In various fields, exploring causal relationships among variables remains an important topic, but this task becomes challenging due to the existence of latent confounders. Ignoring such confounders can lead to false associations and incorrect edge directions. In this paper, we study the linear structural equation model with latent confounders. We propose an algorithm...

    arxiv.org/abs/2609.18535 · PDF

  30. 30

    Provable Guarantees for Spectral Structured Prediction

    Violet Zheng, Jean Honorio

    cs.LG

    Structured prediction is the simultaneous prediction of multiple labels, and is widely used in various fields, such as natural language processing and computer vision. In this paper, we study binary node label recovery on signed graphs with edge-flip noise, a model introduced by (Globerson et al., 2015), via a simple spectral method that decodes node labels from the signs of the principal eigenvector of the noisy signed adjacency matrix. We...

    arxiv.org/abs/2609.18527 · PDF

  31. 31

    Spatially Adaptive Noise Injection

    Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen, Alexandros Kalousis

    cs.LG · stat.ML

    Diffusion samplers reverse a learned noising process using either stochastic (DDPM) or deterministic (DDIM) updates, which represent endpoints of a single family controlled by a scalar noise-injection variance that is applied identically at every spatial location. This uniform approach neglects the geometry of natural images: high-curvature regions such as edges and textures, where the denoiser is uncertain, benefit from stochastic...

    arxiv.org/abs/2609.18466 · PDF

  32. 32

    TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting

    Shunya Nagashima, Yuta Funayama

    cs.LG · cs.AI

    Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information...

    arxiv.org/abs/2609.18407 · PDF

  33. 33

    Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures

    Jens U. Brandt, Noah C. Puetz, Alexander Windmann, Marc Hilbert, Elena Raponi, Thomas Bäck, Thomas Bartz-Beielstein

    cs.LG · cs.AI

    Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail, learning-based predictors can produce physically implausible estimates that propagate to system-level failures. We argue that real-world deployment demands robustness and introduce MuViS-C, the first multi-domain benchmark of robustness against...

    arxiv.org/abs/2609.18396 · PDF

  34. 34

    Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism

    Younes Elberkennou, Dmitri Demler, Thierry Meier, Luca Rispoli, Fanny Lehmann, Joel Oskarsson

    cs.LG · physics.ao-ph

    Despite their high accuracy on point-wise metrics, machine learning weather forecasting models can exhibit different failure modes such as blurring, periodic irregularities, and other unphysical spatial artifacts. This has motivated a variety of metrics to detect known failure cases. Existing metrics fix a representation or transformation in advance, and that choice limits the artifacts they can detect. We propose to train a discriminator for...

    arxiv.org/abs/2609.18381 · PDF

  35. 35

    Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers

    Yihao Ai, Weilong Yan

    cs.LG · cs.AI

    Offline on-policy distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same reuse makes imperfect supervision persistent. Since even strong teachers can fail, we ask \emph{what remains learnable from imperfect teacher supervision?} Teacher failure is only a coarse problem-level signal and does not imply that all supervision along the associated student...

    arxiv.org/abs/2609.18321 · PDF

  36. 36

    Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency

    Jiangfeng Liu, Yanfang Fan

    cs.LG

    Non-intrusive load monitoring (NILM) estimates appliance power sequences from aggregate power, but models trained on source households commonly lose accuracy in unseen households. Aggregate power also contains loads from other appliances and measurement error, so predictions may depend on the residual background that co-occurs with source-household targets. Time-aligned submetered measurements and the additive decomposition of aggregate power...

    arxiv.org/abs/2609.18315 · PDF

  37. 37

    Beyond Quadratic Loss: The Stability Phase Diagram of Adam

    Gaoxiang Tang, Huanran Chen, Ziming Liu

    cs.LG · math.OC · stat.ML

    Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms. For Adam in particular, macroscopic loss spikes have been linked to optimizer dynamics, yet how its two momentum timescales govern them remains unclear. We investigate this dependence by mapping training dynamics across the $(β_1,β_2)$ plane. Across a range of model--task settings, an approximately linear boundary, $1-β_2=C(1-β_1)$,...

    arxiv.org/abs/2609.18314 · PDF

  38. 38

    Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric

    Omran Berjawi, Giuseppe Fenza, Rida Khatoun

    cs.LG

    Large language models (LLMs) are increasingly deployed in applications involving interaction between agents, where their output plays a role in collective reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in...

    arxiv.org/abs/2609.18306 · PDF

  39. 39

    A GAN-Based Framework for Robust DDoS Attack Detection

    Makram Chehayeb, Walid Fahs, Amina Rizk, Rida Khatoun, Omran Berjawi

    cs.LG · cs.CR

    The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks. These attacks are evolving by adopting more complex strategies to evade traditional network security systems. Despite the effectiveness of machine learning models in detecting DDoS traffic, targeted adversarial attacks can degrade their classification accuracy. This work proposes a robust detection framework that...

    arxiv.org/abs/2609.18281 · PDF

  40. 40

    Behavioral Fingerprinting and Navigation Prediction in Web Browsing

    Ralph Elsaghbini, Omran Berjawi, Walid Fahs, Rida Khatoun

    cs.LG

    Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can contain rich and structured behavioral signals. In this work, we conduct a comparative empirical study of two complementary behavioral inference tasks: session-level user identification and next-domain prediction. Both tasks are derived from the same cleaned event stream and evaluated on...

    arxiv.org/abs/2609.18273 · PDF

  41. 41

    F-DACE: Fuzzy Disagreement-Aware Causal Evidence Fusion for Abstention-Safe Conversational Retail Decision Support

    Sourish Dey

    cs.LG

    Observational decision-support systems often expose one causal estimate as a recommendation even when plausible estimators disagree. The inherent engine of the proposed system is causal machine learning: a conditional-average-treatment-effect estimand identified by backdoor adjustment, estimated by an EconML DML causal forest and DoWhy linear regression, checked by two-way fixed effects, and converted into candidate levers by constrained...

    arxiv.org/abs/2609.18238 · PDF

  42. 42

    Anomaly Detection in General Ledger Data: Results from a Hybrid Approach

    Jan Gronewald, Alexander Michael Rombach, Sebastian Stephan, Peter Fettke

    cs.LG

    Journal Entry Tests (JETs) are a mandatory part of annual audits to evaluate and assess both highrisk audit areas and potential material misstatements. However, as JETs are designed to detect known patterns based on domain knowledge, the resulting lists are often very large and require substantial additional effort from the auditor. To ensure the economic efficiency of the audit, the number of false positives in JET result lists must be...

    arxiv.org/abs/2609.18228 · PDF

  43. 43

    APGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study

    Shabir Ahmad Sofi, Bisma Majid, Mir Mohammad Yousuf

    cs.LG · cs.AI · cs.ET

    Quantum Reinforcement Learning (QRL) represents policies as variational quantum circuits (VQCs), making it attractive for combinatorial optimization such as the Capacitated Vehicle Routing Problem (CVRP). On noisy intermediate-scale quantum (NISQ) hardware, however, decoherence degrades fidelity and destabilizes learning, and conventional error mitigation is applied statically without regard to the learning context. We introduce Adaptive...

    arxiv.org/abs/2609.18219 · PDF

  44. 44

    A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification

    Md Taimur Ahad, Ainuddin Ahmed

    cs.LG · cs.AI · cs.CV

    Over the years, Convolutional Neural Networks (CNNs) have demonstrated strong capability in cancer detection and classification using medical images. However, CNN-based models often struggle to capture long-range contextual dependencies. In such scenarios, integrating Compact Convolutional Transformer (CCT) architectures after the CCT layer allows CNN-extracted features to reshape into compact patch tokens using a CCT tokenizer, followed by...

    arxiv.org/abs/2609.18212 · PDF

  45. 45

    Transformation Laws in Neural Representations: Structure, Realisability, and Construction

    Yuan Sun

    cs.LG · cs.NE

    How neural representations preserve the structure of input changes connects representation analysis with internal intervention. We study operable representational content through compatible actions of reference transformations on neural features. We characterise when a transformation descends through an encoder, and give a linear setting in which the defect is governed by the transformation's demand for discarded information, measured in the...

    arxiv.org/abs/2609.18190 · PDF

  46. 46

    MoRE: Mixture of Reused Experts

    Eric S. Qiu, Utku Umur Acikalin, Justin Lovelace, Christian Belardi, Arjun B. Mulchandani, Carla P. Gomes, Kilian Q....

    cs.LG · cs.AI

    Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the number of experts. Recurrent Transformers achieve parameter efficiency by reusing layer weights, but typically lack the capacity for competitive language modeling. We propose Mixture of Reused Experts (MoRE), a hybrid that shares expert pools across groups of adjacent layers. Each layer...

    arxiv.org/abs/2609.18176 · PDF

  47. 47

    LIGE-GR: A Smooth Leap from Ranking to Generative Recommendation in the LLM Era

    Venkat Srinivas, Chenzhang He, Sam Woodmansee, Shawn Lian, Wenjie Hu, Renjie Jiang, Ziheng Huang, Xinyuan Zhang,...

    cs.LG · cs.IR

    The remarkable success of large language models (LLMs) has provided important inspiration for the next generation of recommender systems. Structurally, recommendation and language generation share a similarity: both aim to produce an ordered sequence that optimizes the user's experience. However, how to precisely absorb the essence of the LLM paradigm into mature industrial recommender systems remains an open problem. There are two...

    arxiv.org/abs/2609.18148 · PDF

  48. 48

    Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention

    Yoshiaki Takashita

    cs.LG

    Attention pays, at every layer and for every input, the cost of searching for whom to connect. We ask how far one can get with wiring that is fixed, sparse, and simply rotated from layer to layer. Treating the $n$ positions of a sequence as the vertices of a $\log_2 n$-dimensional hypercube and connecting each position, at layer $\ell$, to its neighbour along dimension $\ell \bmod \log_2 n$, information from every position reaches every other...

    arxiv.org/abs/2609.18145 · PDF

  49. 49

    Rethinking How We Evaluate Methodological Progress in Health AI

    Florent Pollet, Matthew McDermott

    cs.LG · cs.AI

    Methodological progress in artificial intelligence (AI) for electronic health records (EHRs) depends on our ability to determine which algorithms work better, and under which conditions. However, such progress is thought to be hindered by difficulties in reproducibility and in defining clinically meaningful evaluation tasks. We empirically study these barriers by re-implementing 12 historical and recent algorithms within a shared evaluation...

    arxiv.org/abs/2609.18134 · PDF

  50. 50

    Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing

    Eunju Shin, Jongbin Ryu

    cs.LG · cs.CL

    In this paper, we present a Mixture-of-Experts (MoE) quantization method based on activation entropy. Although quantization reduces memory and computational costs, it can substantially degrade performance. In particular, performance decline is pronounced in quantized MoE models, where individual experts have a small number of parameters that are sensitive to low-bit representation. Considering that MoE operates as an ensemble model with...

    arxiv.org/abs/2609.18131 · PDF

  51. 51

    Learning Fractional-Order Dynamics from a Single Trajectory

    Xiaole Zhang, Ziyi Zhang, Zehao Zhao, Stephen Tu, Guannan Qu, Yorie Nakahira, Paul Bogdan

    cs.LG · eess.SY

    Many real-world processes exhibit long-range dependence, where the current state depends on a slowly decaying trace of past states rather than on the most recent state alone. This paper studies system identification for discrete-time fractional-order linear time-invariant systems from a single observed trajectory of length $t$, a setting that captures such non-Markovian dynamics through the Grünwald--Letnikov difference operator. Unlike...

    arxiv.org/abs/2609.18127 · PDF

  52. 52

    FoundAna: A GNN-assisted Foundation Model for Graph Anomaly Detection

    Suprim Nakarmi, Chahana Dahal, Yue Zhao, Junggab Son, Zuobin Xiong

    cs.LG · cs.CR

    Graph anomaly detection aims to identify graph structures (e.g., nodes, edges, or subgraphs) that deviate significantly from expected patterns, which supports critical applications in fraud detection, spam identification, network intrusion, etc. Despite the growing methods in the field, existing approaches follow a one-model-per-dataset paradigm, limiting their transferability across diverse real-world scenarios due to task heterogeneity,...

    arxiv.org/abs/2609.18107 · PDF

  53. 53

    iMINDBench: iEEG Multi-Institution Neural Decoding Benchmark

    Geeling Chau, Saba Hashemi, Yonghyeon Gwon, Eshani Patel, Jan DeWitt, Christopher Wang, Andrii Zahorodnii, Sabera J...

    cs.LG

    Intracranial electroencephalography (iEEG) is widely used to record electrical activity directly from electrodes inside the human brain, making it an attractive modality for neural decoding. However, progress in iEEG decoding, especially toward general-purpose foundation models, remains difficult to measure reliably: datasets are task- or institution-specific, limiting evidence of generalization across tasks and recording environments, and...

    arxiv.org/abs/2609.18104 · PDF

  54. 54

    Agora: Git as Shared Memory for Collective AutoResearch

    Yifan Zhang, Yunheng Zou, Shaokun Zhang, Jian Hu, Hao Zhang, Binfeng Xu, Jan Kautz, Yi Dong

    cs.LG · cs.AI · cs.CL

    Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended. Run several of them and each session starts from scratch, so more agents tend to mean more duplicated search rather than more discovery. Agora is a shared memory for such agents: research is recorded as an append-only directed acyclic graph (DAG) stored in Git, so that every claim is a commit anyone can check out and rerun. Each...

    arxiv.org/abs/2609.18094 · PDF

  55. 55

    FedPGT: Progressive Gradient Transmission for Vehicular Federated Learning over Time-Varying Channels

    Jintao Yan, Tan Chen, Yuxuan Sun, Sheng Zhou, Zhisheng Niu

    cs.LG · cs.IT

    Vehicular federated learning (VFL) enables privacy-preserving collaborative model training for intelligent transportation systems, where communication resource allocation and gradient sparsification techniques have been explored to reduce communication overhead. However, vehicle mobility leads to rapidly varying channel conditions and transmission capacity, rendering predetermined resource allocation and sparsification decisions ineffective....

    arxiv.org/abs/2609.18089 · PDF

  56. 56

    Beyond Embedding Transfer: Component Roles in Grokking Transfer and Stability

    Zeyu Jia

    cs.LG

    Warm-start transfer can make algorithmic tasks generalize rapidly, yet it is unclear which model components provide the gain and whether that gain remains stable under continued optimization. We study cross-operator transfer on modular arithmetic and separate efficacy (early velocity) from stability (post-reach drawdown). In a scale-matched 108-run battery across 12 seed blocks (96-run 2^3 factorial plus 12-run scale control), transferring...

    arxiv.org/abs/2609.18078 · 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.