arXiv:2607. 11684v1 Announce Type: cross Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diversity, while submodular/combinatorial bandits encode diversity in rewards but lack structured choice probabilities.
arXiv:2610. 29067v1 Announce Type: new Abstract: A selective classifier may be claimed to satisfy a risk-coverage contract if some rule from a predeclared menu (a threshold or a union of $K$ score intervals) attains coverage at least $\kappa$ and error at most $\alpha$.
The paper presents a computationally efficient optimal design framework for multinomial logit (MNL) bandits, addressing the combinatorial action space that makes traditional methods infeasible. It introduces two approaches: an exact or certified-approximate mixed-integer linear program with solver‑certified early stopping, and a fully polynomial‑time lifted design using a tractable surrogate objective. Leveraging the Kiefer‑Wolfowitz equivalence theorem, the authors provide near G‑optimality guarantees and apply the framework to develop a best assortment identification algorithm with an instance‑dependent sample complexity of τO((d log N)/Δ²).
arXiv:2608. 06825v1 Announce Type: new Abstract: Learning from correct demonstrations is harder than supervised learning when many answers are correct: after predicting, the learner sees one valid answer but not whether its own answer was valid, nor any reward.
The paper introduces MACCHIATO, a training algorithm that builds a ReLU‑MLP from partial truth‑table data while simultaneously constructing an explicit Boolean circuit over AND, OR, and XOR gates that certifies the network’s computation. The method iteratively projects residuals onto low‑dimensional Boolean classes, compiles the resulting circuit into a ReLU‑MLP, and uses logic minimization and influence‑based variable selection to achieve a six‑layer network with provable truth‑table error bounds. Experiments on synthetic random‑junta tasks show that these certified networks outperform Adam‑trained MLPs in data‑sparse or projection‑aligned regimes and complete faster than flat ESPRESSO in certain settings.
arXiv:2207. 12877v3 Announce Type: replace Abstract: Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework.
A selective classifier may be claimed to satisfy a risk-coverage contract if some rule from a predeclared menu (a threshold or a union of $K$ score intervals) attains coverage at least $κ$ and error a...
The paper introduces belief‑shift branching, a method for placing forks in tree‑structured reinforcement learning rollouts by detecting where a model’s answer belief changes most sharply. Unlike traditional fixed‑length or entropy‑based forking, this approach uses a lightweight probe or learned activation direction to identify pivots in the value curve, reducing unnecessary sampling. Experiments show that belief‑shift forking consistently outperforms baseline methods across multiple models and benchmarks, yielding significant gains in mathematics and code tasks.
arXiv:2607. 11146v1 Announce Type: new Abstract: We study the coupled objective J_K^WOR = E_{S ~ PL-WOR_K}[max_{i in S} R_i]: the expected maximum reward of a size-K Plackett-Luce draw without replacement, the law of Gumbel-Top-K / Stochastic Beam Search decoding.
The paper introduces belief‑shift branching, a method for placing forks in tree‑structured reinforcement learning rollouts by identifying points where a model’s answer belief changes most. Unlike traditional structural or entropy‑based approaches, belief‑shift uses a probe, logit‑lens depth profile, or learned activation direction to locate pivots in the value curve, incurring minimal computational overhead. Experiments across multiple models and benchmarks show that belief‑shift forking consistently outperforms baseline methods, yielding significant gains in mathematics and code tasks.
The paper investigates four ways to grow a classifier—adding a tree level, a hidden unit, a leaf split, and a statistically significant split—under a fixed protocol for tree‑structured and constructive models. It shows that the most natural method of deepening a soft decision tree by duplicating a leaf’s class distribution leaves the gradient of new gates identically zero, preventing learning, and proposes a small random perturbation as a fix. The other three growth decisions each provide a distinct benefit: fitting a new hidden unit to residual error yields a smaller network, splitting the leaf with the largest expected error adds sparsity, and requiring statistical significance before splitting adds no value and reduces accuracy.
Swiss-Knife is a framework that extends decode‑time alignment for frozen language models by treating the alignment specification as a runtime object. It introduces hot‑swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule, and characterises admissible aggregation operators with a representation theorem. In experiments, Swiss‑Knife paired with DPO‑LoRA blades and an uncertainty‑aware pairwise tournament outperforms six existing decode‑time methods, achieving a higher harmonic F1 score, lower refusal rate, and faster objective reconfiguration.