QuaRK: A Quantum Reservoir Kernel for Time Series Learning
arXiv:2602.13531v1 Announce Type: new Abstract: Quantum reservoir computing offers a promising route for time series learning by modelling sequential data via rich quantum dynamics while the only training required happens at the level of a lightweight classical readout. However, studies...
Fast Swap-Based Element Selection for Multiplication-Free Dimension Reduction
arXiv:2602.13532v1 Announce Type: new Abstract: In this paper, we propose a fast algorithm for element selection, a multiplication-free form of dimension reduction that produces a dimension-reduced vector by simply selecting a subset of elements from the input. Dimension reduction is...
Out-of-Support Generalisation via Weight Space Sequence Modelling
arXiv:2602.13550v1 Announce Type: new Abstract: As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However, neural networks...
Interpretable clustering via optimal multiway-split decision trees
arXiv:2602.13586v1 Announce Type: new Abstract: Clustering serves as a vital tool for uncovering latent data structures, and achieving both high accuracy and interpretability is essential. To this end, existing methods typically construct binary decision trees by solving mixed-integer nonlinear optimization...
Optimization-Free Graph Embedding via Distributional Kernel for Community Detection
arXiv:2602.13634v1 Announce Type: new Abstract: Neighborhood Aggregation Strategy (NAS) is a widely used approach in graph embedding, underpinning both Graph Neural Networks (GNNs) and Weisfeiler-Lehman (WL) methods. However, NAS-based methods are identified to be prone to over-smoothing-the loss of node...
Cumulative Utility Parity for Fair Federated Learning under Intermittent Client Participation
arXiv:2602.13651v1 Announce Type: new Abstract: In real-world federated learning (FL) systems, client participation is intermittent, heterogeneous, and often correlated with data characteristics or resource constraints. Existing fairness approaches in FL primarily focus on equalizing loss or accuracy conditional on participation,...
Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling
arXiv:2602.13659v1 Announce Type: new Abstract: Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO) methods bypass backpropagation by...
Advancing Analytic Class-Incremental Learning through Vision-Language Calibration
arXiv:2602.13670v1 Announce Type: new Abstract: Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often compromised by accumulated errors and feature...
On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling
arXiv:2602.13684v1 Announce Type: new Abstract: Correlation Clustering (CC) is a fundamental unsupervised learning primitive whose strongest LP-based approximation guarantees require $\Theta(n^3)$ triangle inequality constraints and are prohibitive at scale. We initiate the study of \emph{sparsification--approximation trade-offs} for CC, asking how...
Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation
arXiv:2602.13706v1 Announce Type: new Abstract: We introduce \texttt{OPO-CMDP}, the first policy optimization algorithm for stochastic Contextual Markov Decision Process (CMDPs) under general offline function approximation. Our approach achieves a high probability regret bound of $\widetilde{O}(H^4\sqrt{T|S||A|\log(|\mathcal{F}||\mathcal{P}|)}),$ where $S$ and $A$ denote...
Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks
arXiv:2602.13746v1 Announce Type: new Abstract: Industrial thermal power systems have coupled performance variables with hierarchical order of importance, making their simultaneous optimization computationally challenging or infeasible. This barrier limits the integrated and computationally scaleable operation optimization of industrial thermal power...
MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models
arXiv:2602.13783v1 Announce Type: new Abstract: While Time Series Foundation Models (TSFMs) have demonstrated exceptional performance in generalized forecasting, their performance often degrades significantly when deployed in real-world vertical domains characterized by temporal distribution shifts and domain-specific periodic structures. Current solutions...
MechPert: Mechanistic Consensus as an Inductive Bias for Unseen Perturbation Prediction
arXiv:2602.13791v1 Announce Type: new Abstract: Predicting transcriptional responses to unseen genetic perturbations is essential for understanding gene regulation and prioritizing large-scale perturbation experiments. Existing approaches either rely on static, potentially incomplete knowledge graphs, or prompt language models for functionally similar...
Cast-R1: Learning Tool-Augmented Sequential Decision Policies for Time Series Forecasting
arXiv:2602.13802v1 Announce Type: new Abstract: Time series forecasting has long been dominated by model-centric approaches that formulate prediction as a single-pass mapping from historical observations to future values. Despite recent progress, such formulations often struggle in complex and evolving settings,...
Fast Physics-Driven Untrained Network for Highly Nonlinear Inverse Scattering Problems
arXiv:2602.13805v1 Announce Type: new Abstract: Untrained neural networks (UNNs) offer high-fidelity electromagnetic inverse scattering reconstruction but are computationally limited by high-dimensional spatial-domain optimization. We propose a Real-Time Physics-Driven Fourier-Spectral (PDF) solver that achieves sub-second reconstruction through spectral-domain dimensionality reduction. By...
AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning
arXiv:2602.13807v1 Announce Type: new Abstract: Time series anomaly detection is critical in many real-world applications, where effective solutions must localize anomalous regions and support reliable decision-making under complex settings. However, most existing methods frame anomaly detection as a purely discriminative...
Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
arXiv:2602.13810v1 Announce Type: new Abstract: Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face...
Pawsterior: Variational Flow Matching for Structured Simulation-Based Inference
arXiv:2602.13813v1 Announce Type: new Abstract: We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained by structured domains, such as bounded physical parameters or hybrid discrete-continuous variables, yet standard flow-matching...
sleep2vec: Unified Cross-Modal Alignment for Heterogeneous Nocturnal Biosignals
arXiv:2602.13857v1 Announce Type: new Abstract: Tasks ranging from sleep staging to clinical diagnosis traditionally rely on standard polysomnography (PSG) devices, bedside monitors and wearable devices, which capture diverse nocturnal biosignals (e.g., EEG, EOG, ECG, SpO$_2$). However, heterogeneity across devices and...
Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks
arXiv:2602.13910v1 Announce Type: new Abstract: Algorithmic stability is a classical framework for analyzing the generalization error of learning algorithms. It predicts that an algorithm has small generalization error if it is insensitive to small perturbations in the training set such...
GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
arXiv:2602.13921v1 Announce Type: new Abstract: Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLMs) are often unsuitable for this task due to context window...
Why Code, Why Now: Learnability, Computability, and the Real Limits of Machine Learning
arXiv:2602.13934v1 Announce Type: new Abstract: Code generation has progressed more reliably than reinforcement learning, largely because code has an information structure that makes it learnable. Code provides dense, local, verifiable feedback at every token, whereas most reinforcement learning problems do...
A Multi-Agent Framework for Code-Guided, Modular, and Verifiable Automated Machine Learning
arXiv:2602.13937v1 Announce Type: new Abstract: Automated Machine Learning (AutoML) has revolutionized the development of data-driven solutions; however, traditional frameworks often function as "black boxes", lacking the flexibility and transparency required for complex, real-world engineering tasks. Recent Large Language Model (LLM)-based...
Proceedings of Machine Learning Research | The Proceedings of Machine Learning Research (formerly JMLR Workshop and Conference Proceedings) is a series aimed specifically at publishing machine learning research presented at workshops and conferences. Each volume is separately titled and associated with a particular workshop or conference. Volumes are published online on the PMLR web site. The Series Editors are Neil D. Lawrence and Mark Reid.
The Proceedings of Machine Learning Research (formerly JMLR Workshop and Conference Proceedings) is a series aimed specifically at publishing machine learning research presented at workshops and conferences. Each volume is separately titled and associated with a particular workshop or conference....
A return to the separation of powers
Please note that SCOTUS Outside Opinions constitute the views of outside contributors and do not necessarily reflect the opinions of SCOTUSblog or its staff. In recent years, the Supreme Court has gradually […]The postA return to the separation of powersappeared...
The art of the circuit split: an explainer
In their petitions for review, litigants spell out – in detail – why the Supreme Court should take up their case. These petitions can cover a wide range of topics, […]The postThe art of the circuit split: an explainerappeared first...
SCOTUStoday for Tuesday, February 17
One of the goals of this newsletter is to demystify the work of the Supreme Court. To that end, we’ve published Closer Looks about why the justices wear black robes, […]The postSCOTUStoday for Tuesday, February 17appeared first onSCOTUSblog.
Assessing States’ Obligations under the UN Guiding Principles on Business and Human Rights Post-Brexit
Private economic actors wield unprecedented influence over the enjoyment of human rights, yet legal systems remain uneven in their regulation of corporate responsibility. Against this backdrop, this article examines a largely underexplored post-Brexit trajectory, the regulatory divergence in the implementation...
Criminalising ‘Conversion Therapy’
An increasing number of jurisdictions have introduced legal bans on so-called ‘conversion therapy’ practices. Yet significant uncertainty and disagreement persist among legal scholars, policymakers and advocates about whether criminal law is an appropriate tool in this area and, if so,...
Is the Electronic Trade Documents Act 2023 Sufficient to Promote the Uptake of Paperless Trading Systems?
In September 2023, the Electronic Trade Documents Act (ETDA) came into force in the UK. It aims to facilitate paperless trade by allowing certain trade documents in electronic form to have the same legal functionality as their paper counterparts. The...