4474 papers
This paper addresses pure exploration problems with potentially infinite answer sets by deriving an instance-dependent lower bound, demonstrating the limitations of existing methods like Sticky Track-and-Stop, and proposing a novel, asymptotically optimal framework called Sticky-Sequence Track-and-Stop.
The paper proposes TSRating, a novel meta-learning framework that leverages LLMs to generate quality comparisons across diverse domains and trains an efficient TSRater model to accurately and adaptively evaluate time series data quality without requiring extensive hypergradient computations.
This paper proposes CORA, a cooperative game-theoretic credit assignment method that utilizes core allocation and coalition sampling to effectively distribute global advantages among agents in multi-agent reinforcement learning, thereby overcoming the limitations of uniform sharing and enhancing coordinated optimal behavior.
This paper introduces two novel model-free algorithms, Q-EarlySettled-LowCost and FedQ-EarlySettled-LowCost, for single-agent and federated reinforcement learning that simultaneously achieve near-optimal regret, linear burn-in costs in state and action spaces, and logarithmic policy switching or communication costs, while also providing improved gap-dependent theoretical guarantees.
The paper introduces ChannelTokenFormer, a unified Transformer-based framework that simultaneously addresses the challenges of complex inter-channel dependencies, asynchronous sampling, and missing values to achieve robust real-world multivariate time series forecasting.
This paper introduces WAFFLE, a pre-training detection algorithm that utilizes Wavelet Scattering Transform or Fourier representations to identify and exclude malicious clients in Federated Learning using compressed, task-agnostic embeddings, thereby improving model robustness without accessing raw data.
This paper introduces the Mixture of Interacting Cascades (MIC), a joint user-topic interaction model based on marked multidimensional Hawkes processes that outperforms existing methods in modeling information spread and provides insightful visualizations of social network activity.
The paper proposes ConLID, a supervised contrastive learning approach that learns domain-invariant representations to significantly improve language identification performance for low-resource languages on out-of-domain data while maintaining accuracy for high-resource languages.
This paper establishes the first global linear convergence guarantees for a dynamic smoothing variant of Iteratively Reweighted Least Squares (IRLS) in robust subspace and affine subspace recovery, extending these theoretical results to nonconvex optimization on Riemannian manifolds and demonstrating their practical utility in low-dimensional neural network training.
This paper proposes a distributed multi-agent best-arm identification algorithm based on linear bandits to optimize service placement in small cell networks, enabling collaborative edge servers to efficiently identify the service that minimizes user latency under unknown demand and dynamic conditions.
This paper establishes new convergence rates for the last iterate of stochastic gradient descent and stochastic heavy ball methods in parametric settings with globally convex or non-convex objectives having -Hölder gradients, utilizing discrete Gronwall's inequality to derive improved bounds without relying on the Robbins-Siegmund theorem.
This study systematically evaluates and enhances DeepONet architectures for geotechnical consolidation problems, demonstrating that a physics-inspired, Fourier feature-enhanced model (Model 4) significantly outperforms standard configurations and achieves up to 1,000-fold computational speedups in 3D scenarios, thereby enabling efficient uncertainty quantification and advancing the integration of scientific machine learning in geotechnics.
The paper introduces LangevinFlow, a physics-inspired sequential Variational Auto-Encoder that models neural latent dynamics using underdamped Langevin equations with a locally coupled oscillator potential, demonstrating superior performance over state-of-the-art baselines in capturing neural population dynamics and decoding behavioral metrics.
This paper introduces Latent Policy Steering (LPS), a method that leverages embodiment-agnostic optical flow to pretrain a World Model on diverse datasets, which is then fine-tuned with limited target-embodiment demonstrations to steer and significantly improve visuomotor policies in low-data regimes.
This paper introduces Multimodal Large Language Model-assisted Evolutionary Search (MLES), a novel framework that combines multimodal LLMs with evolutionary search and visual feedback to automatically generate transparent, verifiable, and human-aligned programmatic control policies that match the performance of deep reinforcement learning methods like PPO.
This paper introduces Clustered Transfer Residual Learning (CTRL), a meta-learning method that combines cross-domain residual learning with adaptive clustering to improve prediction accuracy and preserve source-level heterogeneity across numerous small datasets with distributional shifts, demonstrating superior performance over state-of-the-art benchmarks on five large-scale datasets including a Swiss asylum resettlement program.
This paper proposes and evaluates a novel educational approach that uses AI-generated singing and virtual avatars to transform traditional text-based syllabi into engaging audiovisual performances, demonstrating that this method significantly improves student awareness and recall of critical course information.
MuFlex is a scalable, open-source, physics-based platform that integrates detailed EnergyPlus and Modelica building models with a standardized Reinforcement Learning interface to enable fair benchmarking and effective multi-building demand flexibility coordination, as demonstrated by a 12% peak demand reduction in a four-building case study.
This paper introduces a lightweight, data-efficient Graph Neural Network framework that leverages RFIC domain-informed feature indexing and device-terminal graph abstractions to achieve state-of-the-art accuracy and superior cross-topology generalization in predicting the performance of diverse active radio frequency circuits.
This paper proposes an iterative in-context learning methodology that optimizes few-shot example selection to significantly enhance large language models' systematic generalization and reasoning capabilities on algebraic tasks with non-standard rules, revealing that simpler examples can sometimes outperform complex ones.