Machine Learning

VISA, a new variational inference method, significantly speeds up approximate inference for complex models by reusing model evaluations across multiple gradient steps, achieving comparable accuracy wi…

Learning verified safe neural network controllers for complex nonlinear systems is now possible, achieving an order of magnitude longer safety horizons than state-of-the-art methods while maintaining …

VRCP, a new framework, uses neural network verification to make conformal prediction robust against adversarial attacks, supporting various norms and regression tasks.

VQ-Prompt uses vector quantization to optimize discrete prompts for continual learning, achieving state-of-the-art performance by effectively abstracting task knowledge and optimizing prompt selection…

CatFlow: a novel flow matching method for graph generation, offering superior computational efficiency and performance.

MAST: Train ultra-sparse deep MARL agents with minimal performance loss!

ImagenTime transforms time series into images, leveraging advanced diffusion models for superior generative modeling of both short and long sequences.

Uncertainty-aware HPO boosts iterative learner performance by over 50%, reducing regret and exploration time via a novel UQ-guided scheme.

Neural network efficiency is improved by analyzing weight norm variance across channels to identify optimal layer widths, resulting in reduced parameters and boosted performance.

AI automates mathematical constant formula discovery by analyzing convergence dynamics, revealing known and novel formulas for π, ln(2), and other constants.

ImAD: An end-to-end unsupervised anomaly detection method conquering missing data’s challenge by integrating imputation and detection in a unified framework, achieving superior accuracy!

Strategic data contributors with varying data quality can cause collaborative learning systems to ‘unravel’, but a novel probabilistic verification method effectively mitigates this, ensuring a stable…

MARS, a novel plugin framework, unlocks model-free RL’s intermittent control ability by encoding action sequences into a compact latent space, improving learning efficiency and real-world robotic task…

Linear model transfer learning achieves universal generalization error improvements, depending only on first and second-order target statistics, and defying Gaussian assumptions.

Universal Sample Coding revolutionizes data transmission by reducing bits needed to communicate multiple samples from an unknown distribution, achieving significant improvements in federated learning …

Active learning’s optimal rates are completely characterized, resolving an open problem and providing new algorithms achieving exponential and sublinear rates depending on combinatorial complexity mea…

Universal Physics Transformers (UPTs) offer a unified, scalable framework for efficiently training neural operators across diverse spatio-temporal physics problems, overcoming limitations of existing …

This paper introduces a novel universal online convex optimization algorithm needing only one projection per round, achieving optimal regret bounds for various function types, including general convex…

Universal Neural Functionals (UNFs) automatically construct permutation-equivariant models for any weight space, improving learned optimizer performance and generalization.

UniTS: one model to rule them all! This unified multi-task time series model excels in forecasting, classification, anomaly detection, and imputation, outperforming specialized models across 38 divers…