Roger Wattenhofer
8 papers in the PaperMetrix corpus
Papers by this author
-
Bitcoin meets strong consistency
2016
The Bitcoin system only provides eventual consistency. For everyday life, the time to confirm a Bitcoin transaction is prohibitively slow. In this paper we propose a new system, built on the Bitcoin blockchain, which enables …
-
High Dimensional Clustering with r-nets
2019 · Proceedings of the AAAI Conference on Artificial Intelligence
Clustering, a fundamental task in data science and machine learning, groups a set of objects in such a way that objects in the same cluster are closer to each other than to those in other …
-
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
2024 · arXiv (Cornell University)
Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control, handling perceptual input, and managing …
-
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
2025 · arXiv (Cornell University)
Despite incredible progress, many neural architectures fail to properly generalize beyond their training distribution. As such, learning to reason in a correct and generalizable way is one of the current fundamental challenges in machine learning. …
-
Benchmarking Diarization Models
2025 · arXiv (Cornell University)
Speaker diarization is the task of partitioning audio into segments according to speaker identity, answering the question of "who spoke when" in multi-speaker conversation recordings. While diarization is an essential task for many downstream applications, …
-
Position Paper: Rethinking Privacy in RL for Sequential Decision-making in the Age of LLMs
2025 · arXiv (Cornell University)
The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential decision-making systems where …
-
Human Aligned Compression for Robust Models
2025 · arXiv (Cornell University)
Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learned models (HiFiC and ELIC) against traditional …
-
Recommender Systems for Democracy: Toward Adversarial Robustness in Voting Advice Applications
2025 · arXiv (Cornell University)
Voting advice applications (VAAs) help millions of voters understand which political parties or candidates best align with their views. This paper explores the potential risks these applications pose to the democratic process when targeted by …