[2310.19726] A Path to Simpler Models Starts With Noise
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack
View PDF HTML (experimental) Abstract:The Rashomon set is the set of models that perform approximately equally well on a given dataset, and the Rashomon ratio is the fraction of all models in a given hypothesis space that are in the Rashomon set. Rashomon ratios are often large for tabular datasets in criminal justice, healthcare, lending, education, and in other areas, which has practical implications about whether simpler models can attain the same level of accuracy as more complex models. An open question is why Rashomon ratios often tend to be large. In this work, we propose and study a…
saved by
related reading
- Scaling Laws, Carefully | Lil'Loglilianweng.github.io
- Thinking about High-Quality Human Data | Lil'Loglilianweng.github.io
- The “it” in AI models is the dataset. — Non_Intnonint.com
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- Noisy Data Breaks RLVRddkang.substack.com
- The ML drug discovery startup trying really, really hard to not cheat (Leash Bio)owlposting.com
- MAI-Thinking-1: Building a Hill-Climbing Machinemicrosoft.ai
- The Unreasonable Effectiveness of Easy Training Data for Hard Tasksalexandrabarr.beehiiv.com
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
- AlgZoo: uninterpreted models with fewer than 1,500 parameters — LessWronglesswrong.com
- Papers · Nikhil Garggargnikhil.com
- Scaling Laws Do Not Scalearxiv.org