2214 papers
This paper introduces OptEMA, a novel adaptive Exponential Moving Average optimizer that achieves nearly optimal convergence rates in both stochastic and zero-noise regimes without requiring prior knowledge of Lipschitz constants or manual hyperparameter tuning.
This paper establishes that generative drifting is theoretically equivalent to score matching under Gaussian kernels, providing a spectral and variational framework that explains the empirical superiority of Laplacian kernels, proposes an exponential bandwidth annealing schedule to accelerate convergence, and proves the necessity of the stop-gradient operator through its connection to Wasserstein gradient flows.
The paper introduces SignalMC-MED, a comprehensive benchmark utilizing 22,256 synchronized single-lead ECG and PPG visits to evaluate biosignal foundation models across 20 clinical tasks, demonstrating that domain-specific models with multimodal fusion and full-duration signals outperform general time-series approaches while revealing that larger model sizes do not guarantee superior performance.
This paper introduces the Overfitting-Underfitting Indicator (OUI) as an efficient, early-stage metric based on hidden neuron activation patterns to distinguish optimal learning rates in PPO actor-critic training, demonstrating its superior ability to prune unpromising runs compared to traditional criteria by revealing distinct structural signatures in actor and critic networks.
This paper introduces "neural debuggers," a new class of language models that emulate traditional debugging interactions like setting breakpoints and stepping through code to enable both forward and inverse execution prediction, thereby laying the foundation for more powerful agentic coding systems and automated debugging.
This paper introduces a family of mean-normalized matrix operator norms to derive width-independent smoothness bounds for deep neural networks, leading to the development of MOGA, a row/column-normalized optimizer that enables stable hyperparameter transfer across model widths and outperforms Muon in speed while maintaining competitive performance.
The paper proposes C2FMAE, a coarse-to-fine masked autoencoder that resolves the tension between global semantics and local details in self-supervised learning by employing a cascaded decoder and progressive masking curriculum on a newly constructed multi-granular dataset to achieve hierarchical visual understanding and superior performance across various vision tasks.
This paper demonstrates that reasoning consistently enhances honesty in large language models by guiding them through a representational space where deceptive states are metastable and easily disrupted, ultimately nudging the models toward more stable, honest defaults.
This paper challenges the standard view of superposition in neural networks by demonstrating that, unlike in idealized uncorrelated settings where interference is merely noise, realistic feature correlations allow models to arrange features so that interference becomes constructive, thereby naturally forming the semantic clusters and cyclical structures observed in real language models.
The paper introduces Task-Aware Modulation with Representation Learning (TAM-RL), a novel framework that combines spatio-temporal representation learning with physically grounded constraints to significantly improve the accuracy and generalizability of global terrestrial carbon flux estimates compared to existing state-of-the-art methods.
This paper introduces two online neural network-based algorithms for change-point detection in large time series that demonstrate linear computational complexity, outperform existing methods on various datasets, and are proven to converge to optimal solutions under specific conditions.
This paper presents a white-box support vector machine framework optimized by five meta-heuristic swarm algorithms to monitor the health of toothed milling cutters in real-time by characterizing spindle vibrations and selecting relevant statistical features through Recursive Feature Elimination with Cross-Validation.
This paper provides a comprehensive overview of Automated Reinforcement Learning (AutoRL), surveying existing literature including recent LLM-based techniques, discussing promising non-tailored methods for future integration, and outlining current challenges and research directions in automating MDP modeling, algorithm selection, and hyper-parameter optimization.
This paper proposes an uncertainty-aware, explainable-by-design subsequence-based model that achieves state-of-the-art classification performance for astronomical uncertain time series by incorporating data uncertainty as an input, thereby enabling domain experts to inspect predictions and potentially inspire new theoretical astrophysics developments.
This paper introduces an ensemble Gaussian Process Regression method that significantly reduces computational complexity while outperforming existing machine learning models in predicting US stock returns and constructing superior mean-variance optimal portfolios based on prediction uncertainty.
This paper establishes finite-sample guarantees for a cost-driven representation learning method that learns a latent dynamic model by predicting multi-step costs, enabling the derivation of near-optimal controllers for finite-horizon Linear Quadratic Gaussian (LQG) control problems without explicitly modeling observations or actions.
This paper proposes MU-Mis, a remaining-data-free machine unlearning method that achieves performance comparable to data-dependent approaches by theoretically linking sample contribution to model sensitivity and directly suppressing this sensitivity using only the pre-trained model.
This paper presents a machine learning-focused survey of Computerized Adaptive Testing (CAT), exploring how ML techniques can optimize measurement models, question selection, bank construction, and test control to create more robust, fair, and efficient adaptive assessment systems across various domains.
This paper introduces the NQS-DQME framework, which encodes environmental memory into dissipaton quasiparticles to enable neural quantum states to efficiently and accurately simulate non-Markovian open quantum dynamics with improved scalability and interpretability.
The paper introduces LoRA-Ensemble, a parameter-efficient method that leverages Low-Rank Adaptation to create an implicit ensemble for self-attention networks, achieving superior calibration and accuracy comparable to explicit ensembles while significantly reducing computational and memory costs.