arXiv:2603.19808v2 Announce Type: replace
Abstract: Population-based learning paradigms, including evolutionary strategies, Population-Based Training (PBT), and recent model-merging methods, combine fast within-model optimisation with slower populatio…
arXiv:2602.12023v2 Announce Type: replace-cross
Abstract: Applied work under interference typically models outcomes as functions of own treatment and a low-dimensional exposure mapping of others’ treatments, even when that mapping may be misspecified….
arXiv:2603.23831v1 Announce Type: new
Abstract: Deep neural networks (DNNs), particularly those using Rectified Linear Unit (ReLU) activation functions, have achieved remarkable success across diverse machine learning tasks, including image recognitio…
arXiv:2603.23736v1 Announce Type: cross
Abstract: Many scientific systems, such as cellular populations or economic cohorts, are naturally described by probability distributions that evolve over time. Predicting how such a system would have evolved un…
arXiv:2603.24545v1 Announce Type: cross
Abstract: We study the problem of detecting local geometry in random graphs. We introduce a model $\mathcal{G}(n, p, d, k)$, where a hidden community of average size $k$ has edges drawn as a random geometric gra…
arXiv:2603.23926v1 Announce Type: new
Abstract: Online reinforcement learning in infinite-horizon Markov decision processes (MDPs) remains less theoretically and algorithmically developed than its episodic counterpart, with many algorithms suffering f…
arXiv:2502.02861v4 Announce Type: replace-cross
Abstract: The field of algorithms with predictions incorporates machine learning advice in the design of online algorithms to improve real-world performance. A central consideration is the extent to whic…
arXiv:2511.09500v4 Announce Type: replace-cross
Abstract: We study the problem of denoising when only the noise level is known, not the noise distribution. Independent noise $Z$ corrupts a signal $X$, yielding the observation $Y = X + \sigma Z$ with k…
arXiv:2502.10328v4 Announce Type: replace-cross
Abstract: Markov Chain Monte Carlo (MCMC) algorithms are essential tools in computational statistics for sampling from unnormalised probability distributions, but can be fragile when targeting high-dimen…
arXiv:2603.24392v1 Announce Type: cross
Abstract: Privacy and algorithmic fairness have become two central issues in modern machine learning. Although each has separately emerged as a rapidly growing research area, their joint effect remains comparati…