AI & ML
Learning Multinomial Logits in $O(n \log n)$ time
arXiv stat.ML0 views
arXiv:2601.04423v2 Announce Type: replace-cross 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).
Source:https://arxiv.org/abs/2601.04423PreviousA Bayesian latent class reinforcement learning framework to capture adaptive, feedback-driven travel behaviourNextOn the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
Related posts
How to Read an Avionics BITE Log: A Practical Guide to Making Sense of Fault Data
0dev.to
Time-Series Models in the Streamhouse: Real-Time Forecasting on Streaming Data
0dev.to

UPC vs. APC Fiber Connectors: Why Blue and Green Must Never Mate
0dev.to
“120 users” tells you very little about the workload
0dev.to

On modularization
0dev.to
Is there a standard for AI agent receipts? Yes. Five systems bent around it in one day.
0dev.to