MLINFO COLLECTION
検索拡張生成、文書検索、社内ナレッジQAに関係する論文・実装をまとめます。
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes. Learning risk-sensitive policies from fixed datasets is important when additional…
Conditional generative models parameterized by triangular transport maps are widely used for conditional sampling, yet theoretical guarantees on the quality of the conditional measures they produce…
The neighborhood topology of particle swarm optimization (PSO) determines information propagation and regulates the exploration-exploitation balance. However, existing evaluation methods based on…
Architectural and structural design optimization in parametric software affords about a thousand evaluations of an expensive model for problems with tens of variables, a regime for which most…
We study federated spectral estimation when a large matrix is horizontally partitioned across servers that cannot share raw data. We propose FLICKER, a target-specific gradient-based power iteration…
We study the problem of non-stationary bandits without knowledge of the environmental changes. We propose Detection Augmented Learning (DAL) a black-box paradigm that comprises three modular…
Large language models are trained to predict tokens from a finite vocabulary, each represented by a vector in a $d$-dimensional embedding space. Therefore, token prediction is a classification…
Hybrid forecasting systems combining machine learning and numerical weather prediction offer a promising route toward improved forecast skill while preserving physical consistency. In this study, we…
Neural architecture search (NAS) is expensive, but cross-task transfer can reduce costs by reusing knowledge from previous tasks. However, existing methods struggle with sparse search histories and…
Background-error covariance models are central to atmospheric data assimilation because they spread partial observational information across space, variables, and dynamically coupled scales. Ensemble…
We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with unknown service rates. To model the small buffers…
We prove that the last iterate of Optimistic Follow-The-Regularized-Leader (OFTRL) converges at a linear rate to a Nash equilibrium in multiplayer harmonic games. Our result holds under a mild…
Architecture attribute predictors reduce the cost of neural architecture search by estimating accuracy or latency from a small set of evaluated candidates. The key difficulty is that neural…
We study stationary discrete-time mean-field games with finite state and action spaces under the average-reward criterion, with an entropy-regularized objective and population-dependent dynamics and…
A predictor is multicalibrated with respect to a class of subpopulations (formally, of functions on the inputs, called auditors) if, for every subpopulation in the class and every value the predictor…
The Mallows model is a well-established construct in preference modeling, describing random rankings through their Kendall-Tau distance from a reference permutation. Its compact parameterization and…
We study multiwinner voting with $n$ voters and $m$ candidates, where the goal is to select a committee of size $k$. Voters have unit-sum cardinal utilities but report only coarse information induced…
We study concurrent stochastic games in which a team of agents plays against an adversarial environment. If the agents could access a shared source of randomness, then these games reduce to…
Accurate forecasting models are usually large, expensive to update online, and fixed in architecture once trained. We apply ONE-NAS, an online neuroevolutionary architecture search that evolves a…
Dasgupta, Stevens and Navlakha (2017) showed that the Drosophila olfactory circuit, modelled as a random sparse projection followed by winner-take-all, is a locality-sensitive hash that beats…
We study an online trading problem where a trader, given a sequence of i.i.d. prices drawn from a known distribution $F$ on $[0,1]$, must make irrevocable buy, sell, or hold decisions subject to…
Swarm robotics presents a robust and cost-effective paradigm for advanced automation in complex, dynamic environments, such as those encountered in search and rescue or environmental monitoring. A…
We study last-iterate convergence in unknown two-player zero-sum discounted Markov games with bandit feedback. The players learn independently along a single trajectory without observing each other's…
Evaluating the causal effect of new features is a central goal for online platforms. While recent literature addresses limited testing traffic via centralized portfolio optimization, this perspective…