5 papers
RocketPFN: Accurate Time Series Classification via In-Context Learning
Franco Martino O'Rourke, Ana Trisovic, Dimitris Bertsimas
We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-context classification via a…
A Causal DAG Prior for Synthetic Time-Series Classification Datasets
Franco Martino O'Rourke, Ana Trisovic, Dimitris Bertsimas
A Prior-data fitted Network learns the posterior predictive induced by its training prior; bringing this paradigm to multivariate time-series classification therefore calls for a s…
The Shrinking Lifespan of LLMs in Science
Ana TriÅ¡oviÄ
Scaling laws describe how language model capabilities grow with compute and data, but say nothing about how long a model matters once released. We introduce time-to-peak and lifesp…
On the Origin of Algorithmic Progress in AI
Hans Gundlach, Alex Fogelson, Jayson Lynch +4
Algorithms have been estimated to increase AI training FLOP efficiency by a factor of 22,000 between 2012 and 2023 [Ho et al., 2024]. Running small-scale ablation experiments on ke…
The Rapid Growth of AI Foundation Model Usage in Science
Ana TriÅ¡oviÄ, Alex Fogelson, Janakan Sivaloganathan +1
We present the first large-scale analysis of AI foundation model usage in science - not just citations or keywords. We find that adoption has grown rapidly, at nearly-exponential r…