Demo: Lena Marsh, a sample PhD candidate. The feed was fetched once from real sources and frozen; nothing here calls a model. Build your own profile
Friday 23 October · Multi-fidelity acquisition functions, Constrained optimisation for formulation, Closed-loop autonomous labs and 2 more
arXiv · 2 weeks agoMulti-fidelity acquisition functions
Rikuto Matsumoto, Masanori Ishikura, Masayuki Karasuyama
Why this: Fresh, close to multi-fidelity acquisition functions — pitched at your reading level.
Bayesian optimization often involves multiple objectives, constraints, and fidelity levels
arXiv · yesterdayCalibrated uncertainty for surrogates
Ryan Heejoon Byun, Dayeon Yoon, Won Chang
Why this: Fresh, close to calibrated uncertainty for surrogates — pitched at your reading level.
Computer-model calibration is usually undertaken in service of prediction, yet neither Bayesian Kennedy-O'Hagan (KOH) calibration nor amortized simulation-based inference is built to control the predi
arXiv · 3 weeks agoClosed-loop autonomous labs
Akhlak Mahmood, Janhavi Nistane, Huan Tran, Chiho Kim and 1 more
Why this: Fresh, close to closed-loop autonomous labs — pitched at your reading level.
Polymer informatics has matured from isolated property-prediction studies into an integrated discipline that couples data, models, and decision-making across the polymer design cycle
arXiv · 2 days agoMulti-fidelity acquisition functions
Saman Jayasinghe, Sean Walton, Alma Rahat, Andy Gray and 1 more
Why this: Fresh, close to multi-fidelity acquisition functions — pitched at your reading level.
Comparative judgement uses pairwise comparisons to rank items, but recovering accurate rankings from a limited number of judgements depends on both the inference method and the pairs selected
arXiv · 7 days agoMulti-fidelity acquisition functions
Juho Jung, Seongjae Kang, Jinyoung Han
Why this: Fresh, close to multi-fidelity acquisition functions — pitched at your reading level.
Existing multi-task active learning (MTL-AL) methods predominantly rely on linear scalarization of heterogeneous objectives such as uncertainty, diversity, and gradient conflict
arXiv · 7 days agoMulti-fidelity acquisition functions
Tommaso Ancilli, Thomas Wedenig, Henry Moss, Robert Peharz
Why this: Fresh, close to multi-fidelity acquisition functions — pitched at your reading level.
Bayesian optimization (BO) over discrete spaces is challenging due to missing gradients and the sparsity of valid solutions