MLINFO COLLECTION
少数試行で条件探索を進めるベイズ最適化、実験計画、ブラックボックス最適化を扱います。
Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework that…
The Perception-Adjusted Luce Model (PALM) introduced by by Echenique et al. (2018) is a sequential choice model that can accommodate violations of regularity and choice overload, behaviors not…
Fine-tuning has become a common way to customize text-to-image models, leading to community collections of over 100K lightweight adapters. Adapters sharing a base model can be merged with continuous…
Scientific discovery often requires identifying a small number of high-performing designs in vast, constrained search spaces. This is difficult when evaluations are costly, feasible solutions are…
Bayesian networks for continuous variables often rely on restrictive assumptions: linear Gaussian models lack flexibility to capture nonlinear dependencies, while non-parametric approaches provide…
Iterative combinatorial auctions are used in spectrum allocation, transportation, and industrial procurement, but rounds are costly. We introduce FastCombo, a deep reinforcement learning approach to…
Vision-and-Language Navigation (VLN) requires agents to follow instructions and navigate to target locations. However, current VLN agents often suffer severe performance degradation in unseen…
Semi-implicit variational inference (SIVI) expands the representational capacity of variational families, but optimizing the Evidence Lower Bound (ELBO) remains challenging because the marginal score…
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…
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…
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…
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…
LLMs now prove hard theorems in Lean. Can they also design algorithms and prove their correctness and efficiency?
Bayesian variants of Low-Rank Adaptation (LoRA) provide principled uncertainty estimation when fine-tuning large foundation models, but require specifying the prior over the low-rank weight updates.…
We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values.…
Designing building energy systems is a high-dimensional, mixed-integer search problem: when each design is evaluated by a year-long simulation, black-box optimizers typically need hundreds of…
Hyperdimensional computing (HDC) offers efficient learning and inference for resource-constrained systems, yet ownership verification of its models remains underexplored. We present the first…
We study the Bayesian fixed-confidence best-arm identification problem in which a learner can abstain from making a terminal recommendation. Subject to a target error probability $δ$ and an…
The Gaussian Mumford-Shah model segments an image into regions by minimizing a continuous multivariate Gaussian negative log-likelihood term plus a perimeter penalty. It is used for scalar- and…
Understanding failures of autonomous systems is challenging, particularly when their behavior depends on black-box components such as neural networks. In this work, we make a distinction between two…
We present an AI-assisted mathematical addendum to Strategic Trip Planning: Striking a Balance Between Competition and Cooperation (Amar, 2018). We reconstruct selected relationships between…
Outcome-predictive signals are often treated as promising optimization targets in reinforcement learning, but predictive validity and optimization utility are different claims. We expose this…
Retargeting human motion to humanoids requires preserving motion semantics while accounting for the robot's physical constraints. Kinematic pipelines prescribe a robot trajectory through geometric…
Estimating neural scaling laws involves an end-to-end pipeline: designing a scaling recipe, training models across scales, evaluating models on a target metric, and deploying an algorithm to fit a…