Sample-then-optimize batch neural Thompson sampling
Bayesian optimization (BO), which uses a Gaussian process (GP) as a surrogate to model its
objective function, is popular for black-box optimization. However, due to the limitations of …
objective function, is popular for black-box optimization. However, due to the limitations of …
Unifying and boosting gradient-based training-free neural architecture search
Neural architecture search (NAS) has gained immense popularity owing to its ability to
automate neural architecture design. A number of training-free metrics are recently …
automate neural architecture design. A number of training-free metrics are recently …
A simple yet effective strategy to robustify the meta learning paradigm
Meta learning is a promising paradigm to enable skill transfer across tasks. Most previous
methods employ the empirical risk minimization principle in optimization. However, the …
methods employ the empirical risk minimization principle in optimization. However, the …
Bayesian optimization with cost-varying variable subsets
We introduce the problem of Bayesian optimization with cost-varying variable subsets
(BOCVS) where in each iteration, the learner chooses a subset of query variables and …
(BOCVS) where in each iteration, the learner chooses a subset of query variables and …
Batch Bayesian optimization for replicable experimental design
Many real-world experimental design problems (a) evaluate multiple experimental
conditions in parallel and (b) replicate each condition multiple times due to large and …
conditions in parallel and (b) replicate each condition multiple times due to large and …
Contextual Gaussian process bandits with neural networks
Contextual decision-making problems have witnessed extensive applications in various
fields such as online content recommendation, personalized healthcare, and autonomous …
fields such as online content recommendation, personalized healthcare, and autonomous …
Training-free neural active learning with initialization-robustness guarantees
Existing neural active learning algorithms have aimed to optimize the predictive
performance of neural networks (NNs) by selecting data for labelling. However, other than a …
performance of neural networks (NNs) by selecting data for labelling. However, other than a …
Bayesian optimization under stochastic delayed feedback
Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization
of complex and expensive-to-compute black-box functions. The existing BO methods …
of complex and expensive-to-compute black-box functions. The existing BO methods …
Distributionally robust variational quantum algorithms with shifted noise
Given their potential to demonstrate near-term quantum advantage, variational quantum
algorithms (VQAs) have been extensively studied. Although numerous techniques have …
algorithms (VQAs) have been extensively studied. Although numerous techniques have …
Robust fast adaptation from adversarially explicit task distribution generation
Meta-learning is a practical learning paradigm to transfer skills across tasks from a few
examples. Nevertheless, the existence of task distribution shifts tends to weaken meta …
examples. Nevertheless, the existence of task distribution shifts tends to weaken meta …