2043 papers
This paper establishes that history-dependent policies with sublinear expected regret are robust-optimal for non-rectangular average-reward robust MDPs without requiring rectangularity, and introduces a transient-value framework with an epoch-based policy that achieves constant-order finite-time performance by combining worst-case optimality with online learning.
The paper introduces Missing-by-Design (MBD), a unified framework for revocable multimodal sentiment analysis that combines structured representation learning with a certifiable parameter-modification pipeline to enable the machine-verifiable deletion of specific data modalities while maintaining predictive performance and privacy compliance.
This paper proposes a novel bottleneck transformer architecture that integrates convolutional blocks for frame-level feature extraction and multi-head self-attention for information aggregation to achieve improved non-intrusive prediction of the Short-Time Objective Intelligibility (STOI) metric, outperforming state-of-the-art self-supervised learning models in both seen and unseen scenarios.
This paper proposes a robust, data-driven framework for assortment optimization that maximizes worst-case expected revenue under potential customer preference shifts, establishing computational tractability and deriving statistically optimal algorithms with tight sample complexity bounds to ensure reliable generalization.
This paper rigorously proves that incorporating local updates into the distributed DIGing algorithm can provably accelerate convergence for a broad class of objective functions, demonstrating that two local updates are sufficient to achieve maximal improvement without requiring reduced step sizes.
This study demonstrates that while the multichannel linear descriptors-based block field method (MLD-BFM) achieves the highest accuracy in decoding five finger-joint degrees of freedom from HD sEMG, its performance is not statistically superior to conventional time-domain features, though it significantly outperforms dimensionality reduction methods, highlighting the critical importance of preserving spatial resolution in high-density recordings.
ADHint is a novel reinforcement learning framework that enhances reasoning capabilities and generalization by integrating sample difficulty priors to adaptively schedule hint ratios and employing consistency-based gradient modulation with rollout difficulty posteriors to stabilize learning and prevent destructive imitation.
This paper introduces Decoder-DeepONet (DDON), a novel interpretable operator-learning model that significantly outperforms previous neural network and classical methods in reconstructing electric field profiles from EFISH signals by offering superior accuracy, generalizability, and robustness to incomplete data while identifying optimal sampling windows.
This paper introduces AffPCL, a personalized collaborative learning framework that utilizes affinity-based variance reduction to automatically adapt to unknown heterogeneity among agents, achieving sample complexity improvements that seamlessly interpolate between independent learning and linear speedup without requiring prior knowledge of system similarity.
This paper addresses the challenge of LiDAR-based 3D semantic segmentation under noisy labels and domain shifts by introducing the DGLSS-NL task, establishing a new benchmark, and proposing DuNe, a dual-view framework that achieves state-of-the-art robustness across multiple datasets.
This paper introduces General Policy Composition (GPC), a training-free method that enhances diffusion and flow-based robot policies by theoretically and empirically demonstrating that convexly combining the distributional scores of multiple pre-trained policies at test time yields superior performance and adaptability across diverse tasks.
This paper introduces the Robot Control Stack (RCS), a lean and modular software ecosystem designed to bridge the gap between large-scale Vision-Language-Action model training and real-world robot deployment by unifying simulation and physical control, while validating its effectiveness through extensive evaluations of policies like Octo, OpenVLA, and Pi Zero.
This paper investigates repulsive Monte Carlo methods for computing integrals on the unit sphere, specifically for the sliced Wasserstein distance, by benchmarking determinantal and repelled point processes while analyzing the UnifOrtho estimator to recommend randomized quasi-Monte Carlo for low dimensions and UnifOrtho for high dimensions.
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 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 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.
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.
This paper introduces CDGLT, a training-efficient framework for multimodal metaphor identification that leverages Concept Drift via Spherical Linear Interpolation and adapted LayerNorm tuning to achieve state-of-the-art performance on the MET-Meme benchmark while significantly reducing computational costs compared to existing generative methods.
This paper presents an end-to-end Real2Sim2Real framework for deformable linear object manipulation that employs likelihood-free inference to estimate physical parameter distributions for domain-randomized reinforcement learning, enabling zero-shot deployment of visuomotor policies from simulation to the real world.
This paper demonstrates that simple, local molecular fingerprints combined with LightGBM outperform complex graph neural networks and transformers across 132 peptide datasets, challenging the assumption that modeling long-range interactions is essential for accurate peptide function prediction.