Stefano Ermon

Multi-Agent Adversarial Inverse Reinforcement Learning.

2019 · arXiv (Cornell University)

Reinforcement learning agents are prone to undesired behaviors due to reward mis-specification. Finding a set of reward functions to properly guide agent behaviors is particularly challenging in multi-agent scenarios. Inverse reinforcement learning provides a framework …

Permutation Invariant Graph Generation via Score-Based Generative Modeling

2020 · arXiv (Cornell University)

Learning generative models for graph-structured data is challenging because graphs are discrete, combinatorial, and the underlying data distribution is invariant to the ordering of nodes. However, most of the existing generative models for graphs are …

PiRank: Learning To Rank via Differentiable Sorting.

2020 · arXiv (Cornell University)

A key challenge with machine learning approaches for ranking is the gap between the performance metrics of interest and the surrogate loss functions that can be optimized with gradient-based methods. This gap arises because ranking …

A Unified Framework for Multi-distribution Density Ratio Estimation

2021 · arXiv (Cornell University)

Binary density ratio estimation (DRE), the problem of estimating the ratio $p_1/p_2$ given their empirical samples, provides the foundation for many state-of-the-art machine learning algorithms such as contrastive representation learning and covariate shift adaptation. In …

TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning

2024 · arXiv (Cornell University)

Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e.g., points, polylines, polygons, networks, images, etc.) in their native formats. Learning good spatial representations is a fundamental …