Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Hierarchical Language Model with Predictable Scaling Laws and Provable Benefits of Reasoning
Jason Gaitonde, Frederic Koehler, Elchanan Mossel +2
We introduce a family of synthetic languages with hierarchical structure -- generated by a broadcast process on trees -- for which the role of context length and reasoning in autor…
cs.LG2024
Efficiently learning and sampling multimodal distributions with data-based initialization
Frederic Koehler, Holden Lee, Thuy-Duong Vuong
We consider the problem of sampling a multimodal distribution with a Markov chain given a small number of samples from the stationary measure. Although mixing can be arbitrarily sl…