Machine Learning

BeNeDiff uses generative diffusion models to disentangle and interpret neural dynamics linked to specific behaviors, providing interpretable quantifications of behavior in multi-brain region datasets.

Deep neural network training reveals asymmetric loss valleys, impacting model fusion and federated learning; sign consistency between noise and convergence is key.

LEADS: a novel algorithm learning diverse skills through successor state representations for robust exploration in reward-free environments.

Boost RL performance by solving a series of simplified MDPs before tackling the complex real-world one!

RECURVE: A novel boundary detection method leveraging representation trajectory curvature, surpassing state-of-the-art techniques by accommodating both gradual and abrupt changes in time series.

Expected Probabilistic Hierarchies (EPH) offers a novel, scalable approach to hierarchical clustering by optimizing expected scores under a probabilistic model, outperforming existing methods on vario…

Boost RL efficiency in continuous action spaces by masking irrelevant actions using three novel continuous action masking methods!

Low Precision Ensembling (LPE) boosts large model accuracy using training-free ensemble creation via stochastic rounding in low-precision number systems.

Evidential Mixture Machines (EMM) enhances multi-label active learning by deciphering label correlations for improved accuracy and uncertainty quantification in large, sparse label spaces.

Spexphormer achieves significant memory reduction in graph Transformers by leveraging a two-stage training process that leverages attention score consistency across network widths to effectively spars…

This paper provides the first complete error analysis for diffusion models, theoretically justifying optimal training and sampling strategies and design choices for enhanced generative capabilities.

Shapley-based Cooperation Enhancing Multi-view Clustering (SCE-MVC) improves deep multi-view clustering by using game theory to fairly evaluate and enhance individual view contributions.

Deep random features enable efficient Euclidean distance compression, offering improved bit storage compared to linear methods for specific parameter ranges, thus significantly advancing high-dimensio…

HyperDM accurately estimates both epistemic and aleatoric uncertainty using a single model, overcoming the computational limitations of existing ensemble methods.

Boosting neural network robustness against weight errors, this research leverages neural tangent kernels to theoretically explain and optimize error-correcting output codes (ECOCs), achieving superior…

This research paper presents a novel theoretical error analysis for the spherically constrained least squares (SCLS) method used to solve Stackelberg prediction games (SPGs). SPGs model strategic int…

Equivariant Neural Diffusion (END) revolutionizes 3D molecule generation with a learnable forward process, achieving state-of-the-art results and enhanced controllability.

Nonlinear spectral filters (NLSFs) enable fully equivariant graph neural networks, improving accuracy and generalization.

Equivariant Blurring Diffusion (EBD) generates 3D molecular conformers hierarchically, first creating coarse-grained fragments then refining atomic details, significantly outperforming existing method…

RL agents make better decisions by simulating future scenarios, considering diverse agent behaviors, and using character inference for improved decision-making.