Machine Learning

Global Convergence of Policy Gradient in Average Reward MDPs

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models

On Bits and Bandits: Quantifying the Regret-Information Trade-off

Classifier-Guided Captioning Across Modalities

Directed Graph Generation with Diffusion Kernels

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models

Diffusion inversion is the problem of taking an image and a text prompt that describes it and finding a noise latent that would generate the exact same image. Most current deterministic inversion techniques operate by approximately solving an …

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Topological deep learning (TDL) is a rapidly growing field that seeks to leverage topological structure in data and facilitate learning from data supported on topological objects, ranging from molecules to 3D shapes. Most TDL architectures can be …

GL-Equivariant Processing of Low-Rank Weight Spaces

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks

Graph spectra are an important class of structural features on graphs that have shown promising results in enhancing Graph Neural Networks (GNNs). Despite their widespread practical use, the theoretical understanding of the power of spectral …