Andreas Krause

Safe Model-based Reinforcement Learning with Stability Guarantees

2017 · arXiv (Cornell University)

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a …

Differentiable Submodular Maximization

2018

We consider learning of submodular functions from data. These functions are important in machine learning and have a wide range of applications, e.g. data summarization, feature selection and active learning. Despite their combinatorial nature, submodular …

Active Bayesian Causal Inference

2022 · arXiv (Cornell University)

Causal discovery and causal reasoning are classically treated as separate and consecutive tasks: one first infers the causal graph, and then uses it to estimate causal effects of interventions. However, such a two-stage approach is …

Amortized Inference for Causal Structure Learning

2022 · arXiv (Cornell University)

Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior knowledge is …

Rao-Blackwellizing the Straight-Through Gumbel-Softmax Gradient\n Estimator

2020 · arXiv (Cornell University)

Gradient estimation in models with discrete latent variables is a challenging\nproblem, because the simplest unbiased estimators tend to have high variance.\nTo counteract this, modern estimators either introduce bias, rely on multiple\nfunction evaluations, or use learned, …

Lazier Than Lazy Greedy

2015

Is it possible to maximize a monotone submodular function faster than the widely used lazy greedy algorithm (also known as accelerated greedy), both in theory and practice? In this paper, we develop the first linear-time …

Provably Learning Nash Policies in Constrained Markov Potential Games

2023 · arXiv (Cornell University)

Multi-agent reinforcement learning (MARL) addresses sequential decision-making problems with multiple agents, where each agent optimizes its own objective. In many real-world instances, the agents may not only want to optimize their objectives, but also ensure …

Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning

2025 · arXiv (Cornell University)

Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In this work, we study the test-time scaling of language …