MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Typed decision models return a probability distribution over options supplied by the caller, and software tends to act on that number as if it were a guarantee. We measure what it licenses, comparing…
We study how learning algorithm design shapes equilibrium selection in infinite-horizon discounted Markov games with finite states and actions. Each episode, players choose smooth best responses to…
We study the computational complexity of clairvoyant strategy optimization against a known online learner in finite-horizon repeated games. In general-sum games with bounded payoffs, unless…
Improving on a baseline requires exploring away from it, precisely where its performance may be lost. We propose DUET (Doubling Under Empirical Tests), a horizon-free phased mixing scheme for…
Spiking neural networks (SNNs) encode information not only in whether neurons fire but also in when they fire, and this temporal dimension shapes what a trained network reveals about its training…
Two compass bearings near north can have an ordinary arithmetic mean pointing south: the difficulty is that angles live on a circle, not a straight line. Using real wind observations, diffusion-MRI…
We study score matching over finite-dimensional approximation spaces generated by gradients of eigenfunctions of the infinitesimal generator of a forward diffusion. We compare polynomial…
Dynamical coarse-graining of neural networks gives macroscopic observables and enables training to be predicted, and controlled in a state space far smaller than the parameter space. In this paper,…
Nonparametric inference often requires characterizing an unknown function, such as a cumulative distribution function (CDF), across its entire domain rather than a specific point. We develop…
If rotating a problem never changes its answer, one might expect its best model to be rotation-invariant; we show that this fails, predictably and by an exact amount, when capacity is limited. A…
Semiparametric Bayesian networks (SPBNs) are flexible probabilistic graphical models for representing joint distributions of continuous variables through lower-dimensional conditional probability…
We study full-information online linear optimisation on the unit $\ell_p$ ball in $\mathbb{R}^d$, for fixed $2\le p<\infty$ and losses of dual norm at most one. Let $Δ_T$ denote the cumulative loss…
Accelerated dynamics methods, such as parallel replica dynamics, require estimates of the decorrelation time, after which a process trapped in one of its metastable states is distributed according to…
Dynamic creative optimization decides which creative of an ad to render for each request. Recent work places that choice before ad ranking, but relies on deterministic point predictors with no…
We introduce a Stein variational framework for sampling from a target density $p\propto e^{-U}$ when the target potential $U$ is possibly non-smooth. The key idea is to introduce a smoother reference…
Wind farm layout optimization becomes increasingly difficult as turbine count grows, especially when high-fidelity aerodynamic models are used. Conventional Kriging-based Bayesian optimization often…
The Hylland-Zeckhauser (HZ) mechanism provides a market-based approach to one-sided matching, making efficient equilibrium computation central to its implementation. Bi-valued utilities admit a…
Shapley-value-based explanations are widely used for feature attribution in machine learning. However, in computer vision, a feature may reduce the target-class score when added to the complete…
Statistical procedures often control expected loss at a prescribed level while leaving part of their risk budget unused. Building on the e-value representation of risk-controlled decisions and the…
Many academic disciplines (in particular, mathematics and the theoretical sciences) face difficult questions about how to adapt their practices to the rise of highly capable artificial intelligence…
Model selection and hyperparameter tuning pose a central challenge in off-policy evaluation (OPE) because errors of fitted Q-functions and occupancy-ratio estimates cannot be directly evaluated from…
Computing local-level variable importance (VI) is critical for understanding machine learning models. Local permutation-based VI metrics offer a simple yet powerful approach, measuring how much a…
Multi-objective reinforcement learning is a fundamental problem for modern AI, with applications spanning post-training, reasoning models, and robotic control. A central challenge is to learn…
Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on…