We study reinforcement learning for episodic Markov Decision Processes (MDPs) whose transitions are modelled by a multinomial logistic (MNL) model. Existing algorithms for MNL mixture MDPs yield a regret of $\smash{\tilde{O}(dH^2\sqrt{T})}$ (Li et al., 2024), where $d$ is the feature dimension, $H$ the episode length, and $T$ the number of episodes. Inspired by the logistic bandit literature (Abeille et al., 2021; Faury et al., 2022; Boudart et al., 2026), we introduce a problem-dependent constant $\barσ\_T \leq 1/2$, measuring the normalised average variance of the optimal downstream value function along the learner's trajectory. We propose an algorithm achieving a regret of $\smash{\tilde{O}(dH^2\barσ\_T\sqrt{T})}$, which recovers the existing bound in the worst case and improves upon it for structured MDPs. For instance, for KL-constrained robust MDPs, $\barσ\_T = O(H^{-1})$, reducing the horizon dependence by a factor $H$. We further establish a matching $\smash{Ω(dH^2\barσ\_T\sqrt{T})}$ lower bound, proving minimax optimality (up to logarithmic factors) and fully characterising the regret complexity of MNL mixture MDPs for the first time.

Neural Information Processing Systems http://nips.cc/

Mixability has been shown to be a powerful tool to obtain algorithms with optimal regret. However, the resulting methods often suffer from high computational complexity which has reduced their practical applicability. For example, in the case of multiclass logistic regression, the aggregating forecaster (Foster et al. (2018)) achieves a regret of O(log(Bn)) whereas Online Newton Step achieves O(eBlog(n)) obtaining a double exponential gain in B (a bound on the norm of comparative functions). However, this high statistical performance is at the price of a prohibitive computational complexity O(n37). In this paper, we use quadratic surrogates to make aggregating forecasters more efficient. We show that the resulting algorithm has still high statistical performance for a large class of losses. In particular, we derive an algorithm for multi-class logistic regression with a regret bounded by O(Blog(n)) and a computational complexity of only O(n4).

In this paper, we analyze neural networks trained on high-dimensional data that lies on a low dimen-441 sional linear subspace denoted by P. We assume that the dimension of P is d ℓ. Throughout the pa-442 per it will be more convenient to analyze data which lies on the subspace M = span({e1,...,ed ℓ}),443 because then the "off manifold" directions correspond exactly to certain coordinates of the input. In444 this section we show that we can essentially analyze the data as if it is rotated to lie on M, and it445 would imply the same consequences as the original data from P.446 Theorem A.1. Let P Rd be a subspace of dimension d ℓ, and let M = span{e1,...,ed ℓ}.447 Let R be an orthogonal matrix such that R P = M, let X P be a training dataset and let448 XR = {R x: x X}.

A series of recent publications by Awasthi, Mao, Mohri, and Zhong [2022b] have introduced the key notion of H-consistency bounds for surrogate loss functions. These are upper bounds on the zero-one estimation error of any predictor in a hypothesis set, expressed in terms of its surrogate loss estimation error. They are both non-asymptotic and hypothesis set-specific and thus stronger and more informative than Bayes-consistency. However, determining if they hold and deriving these bounds have required a specific proof and analysis for each surrogate loss. Can we derive more general tools and characterizations?