Learning Multinomial Logits in $O(n \log n)$ time
Abstract
A Multinomial Logit (MNL) model is composed of a finite universe of items $[n]=\{1,\dots,n\}$, each assigned a positive weight.
A query specifies an admissible subset---called a slate---and the model chooses one item from that slate with probability proportional to its weight.
This query model is also known as the Plackett--Luce model or conditional sampling oracle in the literature.
Although MNLs have been studied extensively, a basic computational question remains open: given query access to slates, how efficiently can we learn weights so that, for every slate, the induced choice distribution is within total variation distance $\varepsilon$ of the ground truth?
This question is central to MNL learning and has direct implications for modern recommender system interfaces.
We provide both adaptive and non-adaptive algorithms for this task.
Our first adaptive algorithm makes $O(\frac{n\log n}{\varepsilon^2})$ queries and learns every choice distribution in total variation distance $\varepsilon$.
We also provide a second adaptive algorithm that with $O(\frac{n \log n}{\varepsilon^3})$ queries provides a stronger guarantee: each choice distribution is approximated to a multiplicative $1\pm\varepsilon$ error (except for subsets of mass smaller than $\varepsilon$).
We complement these algorithms with lower bounds of $\Omega(\frac{n\log n}{\varepsilon^2})$ for total variation distance and $\Omega(\frac{n \log n}{\varepsilon^3})$ for the multiplicative error guarantee, showing the optimality of our adaptive algorithms.
Our non-adaptive algorithm makes $O\left(\frac{n^{2}}{\varepsilon^{3}}\log n \log\frac{n}{\varepsilon}\right)$ queries to obtain guarantees under the multiplicative error notion.
We complement this result with an $\Omega(\frac{n^2 \log n}{\varepsilon^2})$ lower bound for any non-adaptive algorithm, showing that our algorithm is almost tight in $n$ (within a $\log n$ factor).