While dataset condensation effectively enhances training efficiency, its application in on-
device scenarios brings unique challenges. 1) Due to the fluctuating computational …

Most dataset distillation methods struggle to accommodate large-scale datasets due to their
substantial computational and memory requirements. In this paper, we present a curriculum …

Dataset distillation, a pragmatic approach in machine learning, aims to create a smaller
synthetic dataset from a larger existing dataset. However, existing distillation methods …

Data-efficient learning has garnered significant attention, especially given the current trend
of large multi-modal models. Recently, dataset distillation has become an effective approach …

Data-efficient learning has drawn significant attention, especially given the current trend of
large multi-modal models, where dataset distillation can be an effective solution. However …

Active learning parallelization is widely used, but typically relies on fixing the batch size
throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off …

Though dataset distillation has witnessed rapid development in recent years, the distillation
of multimodal data, eg, image-text pairs, poses unique and under-explored challenges …

Bayesian methods provide an elegant framework for estimating parameter posteriors and
quantification of uncertainty associated with probabilistic models. However, they often suffer …

A Bayesian pseudocoreset is a compact synthetic dataset summarizing essential information
of a large-scale dataset and thus can be used as a proxy dataset for scalable Bayesian …

Optimization-based techniques for federated learning (FL) often come with prohibitive
communication cost, as high dimensional model parameters need to be communicated …