MLINFO COLLECTION
材料候補探索、分子生成、実験条件探索、ベイズ最適化に関係する技術です。
While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via…
Replicator dynamics, the central model of evolutionary game theory, describe populations evolving under selection and agents learning by trial and error. They also admit a third use: continuous-time…
Many decision-making tasks are inherently multi-objective. Interactive evolutionary multi-objective optimization algorithms (iEMOAs) are particularly well-suited to help the decision-maker find their…
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large language model (LLM) agents offer a new way to…
Frameworks that use large language models for scientific discovery typically rely on a fixed, human-designed algorithm that decides what the model sees at each step, leaving the model only the role…
As constellations of satellite grow in size, and become more costly, they are increasingly funded by multiple stakeholders who expect access to the constellation's resources that is commensurate with…
Distributionally robust optimization (DRO) hedges data-driven two-stage stochastic programs against error in the distribution estimated from a finite record, and standard ambiguity sets differ in how…
The advent of large, high-density FPGAs such as the AMD Versal enables efficient hardware implementation of neuromorphic Ising machines, unlocking unprecedented performance for complex combinatorial…
Conventional wheel-equipped quadrotor UAVs must tilt their bodies to generate lateral forces, limiting their ability to maintain a desired attitude during lateral motion. This paper proposes a…
In low-rank matrix sensing of a rank-$D$ factor $U^\ast \in \mathbb{R}^{V \times D}$, replacing isotropic Gaussian designs with power-law measurement covariance $Σ= \mathrm{diag}(j^{-s})_{j=1}^V$…
Controlling dynamical systems governed by partial differential equations (PDEs) remains a challenging task in scientific computing, owing to high-dimensional state spaces, distributed actuation,…
Automated mechanism design has enabled the learning of complex auction mechanisms using neural networks. However, designing non-truthful auctions remains challenging because bidders' equilibrium…
Decision-making under uncertainty remains a key issue in Machine Learning (ML), particularly in the deployment of safety-critical systems, where reliable quantification of system behavior is…
Continuous relaxations are commonly used as an encoding scheme for evolutionary multitasking optimization (EMTO), allowing heterogeneous tasks to be optimized within a unified search space. However,…
Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is…
AdaGrad-style methods can simultaneously adapt to both the order and constants of smoothness in centralized optimization. However, existing extensions to federated optimization with heterogeneous…
Using machine learning, we identify a second transition in polymer chain stretching driven by planar elongational flow, beyond the well-known coil-stretch transition. We achieve this by developing a…
A central topic in online and stochastic optimization is to design algorithms that do not require tuning of hyperparameters. Successful strategies in online learning include AdaGrad-style learning…
AI infrastructure, the chips and software that train and serve AI models, is designed in layers. Layers make the system manageable, but they also fix which choices an optimizer can consider.
This paper considers coordinating a heterogeneous team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) traversing a domain containing an unknown number of potentially hazardous…
Game AI results are comparable only when different implementations expose the same decision problem. Yet seemingly minor representation choices can silently change that problem by altering action…
Visual commissions require image agents to integrate heterogeneous source materials, preserve requirements across dependent stages, and produce coordinated deliverables. Existing evaluations examine…
Discounted regret measures the performance of an online learner by assigning exponentially decaying weights to past losses, reflecting the greater importance of recent losses in non-stationary online…
What is the round complexity of Hessian-similar optimization when each round can contact at most $s$ of $m$ clients? Prior rates permit a free master or full participation and do not characterize…