11739 papers
This paper proposes a novel, implementable adaptive parameter selection strategy for kernel-based gradient descent that integrates bias-variance analysis with the splitting method and empirical effective dimension to achieve optimal generalization error bounds across diverse kernels, target functions, and error metrics.
This paper introduces heterogeneous time steps (HTS) to Equilibrium Propagation, demonstrating that assigning neuron-specific time constants drawn from biologically motivated distributions improves training stability and robustness while maintaining competitive performance.
This paper introduces the Surprisal-Rényi Free Energy (SRFE), a novel log-moment-based functional that bridges forward and reverse Kullback-Leibler divergences by revealing a mean-variance tradeoff and providing a variational characterization that controls large deviations in code-length, thereby clarifying the geometric and statistical structure underlying these distinct learning objectives.
This paper introduces a simple variant of the Squint algorithm for the classic expert problem and proves, via a straightforward modification of the original proof, that it achieves a regret bound similar to that of a recent variant of the NormalHedge algorithm.
This paper proposes a scalable, contrastive causal discovery model that leverages paired observational and single-regime soft interventional data to construct globally consistent causal structures, theoretically proving its ability to recover identifiable edges and outperform non-contrastive methods in both in-distribution and out-of-distribution scenarios.
This replication study of FairDICE, a multi-objective offline reinforcement learning algorithm, reveals that while its theoretical claims hold, a critical code error initially reduced it to standard behavior cloning and underspecified hyperparameters hindered reproducibility, though corrected experiments demonstrate its potential to scale to complex environments despite a reliance on online tuning.
This paper demonstrates that a significant portion of transformer MLP nonlinearity is redundant and context-dependent, showing that a lightweight gating mechanism can dynamically replace these computations with linear surrogates to reduce computational waste or, when applied strategically with full retraining, actively improve model performance by eliminating harmful nonlinearities.
This paper introduces Graph Hopfield Networks, an energy-based framework that unifies associative memory retrieval with graph Laplacian smoothing to achieve state-of-the-art node classification performance and enhanced robustness across diverse graph benchmarks.
This paper challenges the conventional practice of stopping diffusion model training at the minimum test loss by identifying a "biased generalization" phase where models continue to lower loss while overfitting to training data, a phenomenon driven by the sequential nature of feature learning that poses risks for privacy-critical applications.
This paper reveals that state-of-the-art mathematical reasoning models often achieve high benchmark accuracy through computationally unstable and unfaithful pathways, masking significant rates of silent failures and demonstrating that increased model scale does not necessarily improve reliability or correctness.
This paper proposes a minimax optimal algorithm for tabular reinforcement learning with delayed state observations that combines augmentation and upper confidence bound methods to achieve a regret bound of , which is proven to be optimal up to logarithmic factors.
The paper introduces PERSIST, a novel world model paradigm that simulates the evolution of a latent 3D scene to overcome the spatial memory and consistency limitations of existing video generation methods, thereby enabling coherent, long-horizon interactive experiences with persistent 3D state and geometry-aware control.
This paper introduces MasCOR, a machine-learning-assisted framework that overcomes the computational limitations of traditional mathematical programming to enable rapid, near-optimal co-optimization of e-fuel system design and real-time operation under renewable uncertainty, demonstrating site-specific strategies for cost-effective carbon-neutral methanol production across diverse European locations.
This paper addresses the critical reliability challenges in Compute-in-Memory neural accelerators caused by device non-idealities by demonstrating the disproportionate impact of small variations on safety-critical workloads and proposing cross-layer solutions, including a selective write-verify mechanism (SWIM) and noise-aware training, to ensure robust and efficient deployment.
This paper introduces a diagnostic framework demonstrating that rankings of gene regulatory network inference methods exhibit significant instability across evaluation protocol axes, driven primarily by shifts in relative discrimination ability rather than base rate effects, thereby challenging the assumption of ranking invariance in current benchmarking practices.
This study proposes a novel Geographically-Weighted Weakly Supervised Bayesian High-Resolution Transformer that fuses Sentinel-1, RCM, and AMSR2 data to generate 200m resolution pan-Arctic sea ice concentration maps with reliable uncertainty estimates, effectively overcoming challenges related to subtle feature extraction, inexact labels, and data heterogeneity.
This paper argues that adversarial examples arise from an exponential misalignment between the high-dimensional perceptual manifolds of neural networks and human concepts, suggesting that achieving robustness requires aligning these dimensions to match human perception.
This paper introduces OrbEvo, an equivariant graph transformer model that efficiently predicts time-dependent electronic wavefunctions and related physical properties under external fields by learning to evolve orbital coefficients through autoregressive rollout, thereby overcoming the computational bottlenecks of conventional real-time time-dependent density functional theory.
The paper introduces the MMAI Gym for Science, a comprehensive framework for training efficient, purpose-built Liquid Foundation Models that outperform larger general-purpose and specialist models on critical drug discovery tasks by mastering the specific "language of molecules."
This paper proposes Q-Measure-Learning, an efficient online reinforcement learning algorithm for continuous state spaces that represents the action-value function as a signed empirical measure updated via coupled stochastic approximation, achieving almost sure convergence to a kernel-smoothed Bellman fixed point with linear memory and computational complexity.