3821 papers
This paper establishes the convergence of Dual Space Preconditioned Gradient Descent to an interpolating solution for overparameterized linear models using novel Bregman divergence techniques, while characterizing its implicit bias to show that isotropic preconditioners recover standard gradient descent solutions and general preconditioners yield solutions within a constant factor of the standard solution.
The paper introduces JEDI, a hierarchical model that jointly learns shared embeddings over recurrent neural network weights to robustly infer generalizable, task-specific neural dynamics from noisy, high-dimensional experimental recordings, successfully recovering underlying mechanistic structures and providing insights into motor control.
This paper introduces a universal, nearest-neighbor-based estimator for intrinsic dimensionality that achieves state-of-the-art performance through simple calculations and theoretical guarantees of convergence independent of the underlying data distribution.
The paper introduces VERI-DPO, an evidence-aware alignment framework that leverages claim verification to mine preference pairs for Direct Preference Optimization, significantly reducing unsupported claims and improving the faithfulness of clinical summarizations while maintaining informative length.
This paper introduces the tubal tensor train (TTT) decomposition, a novel tensor network model that integrates t-product algebra with the tensor train structure to achieve linear storage scaling for high-order tensors, and validates its effectiveness through efficient algorithms and applications in image/video compression, tensor completion, and hyperspectral imaging.
This paper proposes a lightweight hybrid framework for the Game of the Amazons that integrates Graph Attention Autoencoders, Stochastic Graph Genetic Algorithms, and GPT-4o-mini to overcome resource constraints, achieving decision accuracy improvements of 15%–56% over baselines and outperforming its teacher model by effectively denoising LLM outputs through structural graph reasoning.
The paper introduces IH-Challenge, a reinforcement learning dataset designed to enhance instruction hierarchy robustness in frontier LLMs, which significantly improves their ability to prioritize instructions against conflicts and adversarial attacks while maintaining helpfulness and minimizing capability regression.
This paper proposes a world model framework for lithium-ion battery degradation prognosis that encodes cycle data into latent states and propagates them forward using learned dynamics, demonstrating that iterative rollout significantly reduces trajectory forecast error compared to direct regression while a Single Particle Model constraint specifically enhances prediction accuracy at the degradation knee.
This paper presents a Multi-Agent Reinforcement Learning framework using Proximal Policy Optimization to coordinate UAV fleets for time-critical medical supply delivery, demonstrating that classical PPO outperforms asynchronous and sequential strategies in dynamically prioritizing tasks and reallocating resources under uncertain conditions using real-world geographic data.
This paper introduces Group Relative Reward Rescaling (GR), a novel reinforcement learning method that effectively mitigates length inflation in large language models by reframing length control as a multiplicative rescaling paradigm, thereby achieving lossless optimization and superior performance compared to existing baselines without compromising downstream capabilities.
The paper introduces SCORE, a lightweight deep learning architecture that replaces traditional layer stacking with a weight-shared, ODE-inspired contractive recurrent update mechanism to improve training stability, accelerate convergence, and reduce parameter counts across various model types.
This paper proposes a reinforcement learning approach that automatically tunes cluster scheduler scoring weights using percentage improvement rewards, frame-stacking, and limited domain information to significantly improve end-to-end job performance across diverse workloads and cluster setups.
This paper introduces a machine learning framework that utilizes a directed bipartite graph to model time-ordered predictive linkages between U.S. and Chinese equity markets, revealing a significant directional asymmetry where U.S. returns strongly predict Chinese intraday performance while the reverse effect is limited.
This paper establishes theoretical conditions under which Monotone Operator Equilibrium Networks maintain convergence and bounded error under weight quantization by analyzing spectral perturbations, and validates these findings through experiments showing that quantization-aware training can recover provable convergence at four-bit precision.
This paper introduces the Riemannian geometry-preserving variational autoencoder (RGP-VAE), a generative model that produces high-fidelity, symmetric positive-definite synthetic EEG covariance matrices to effectively augment data and enhance performance in motor imagery brain-computer interface applications.
This paper demonstrates that Transformers performing in-context learning on binary hypothesis testing tasks effectively approximate Bayes-optimal statistical estimators by dynamically adapting their internal decision mechanisms—ranging from voting-style ensembles for linear tasks to deeper sequential computations for nonlinear ones—rather than relying on simple similarity matching or fixed heuristics.
The paper introduces HAPEns, a novel post-hoc ensembling method for tabular data that constructs diverse ensembles along the Pareto front of predictive performance and hardware efficiency, significantly outperforming existing baselines across 83 datasets by explicitly balancing accuracy with resource constraints.
This paper empirically demonstrates that contrary to the hypothesis that moral reasoning alignment requires diversity-seeking algorithms, standard reward-maximizing RLVR methods are equally or more effective because high-reward moral responses exhibit a concentrated distribution in semantic space similar to logical reasoning tasks.
This paper establishes a mathematical framework called Gradient Flow Drifting that proves the equivalence between the recently proposed Drifting Model and the Wasserstein gradient flow of the forward KL divergence under KDE approximation, while extending the approach to a mixed-divergence strategy on Riemannian manifolds to simultaneously mitigate mode collapse and blurring.
This technical note presents a JAX-compatible implementation of the Self-Scaled Broyden family of quasi-Newton methods, including BFGS, DFP, and Broyden variants with Zoom line search, built upon the Optimistix library to facilitate their adoption within the JAX community.