Related papers: Efficient Dataset Selection for Continual Adaptati…

With promising empirical performance across a wide range of applications, synthetic data augmentation appears a viable solution to data scarcity and the demands of increasingly data-intensive models. Its effectiveness lies in expanding the…

This thesis investigates dataset downsampling as a strategy to optimize energy efficiency in recommender systems while maintaining competitive performance. With increasing dataset sizes posing computational and environmental challenges,…

Data-Driven Predictive Control (DPC) optimizes system behavior directly from measured trajectories without requiring an explicit model. However, its computational cost scales with dataset size, limiting real-time applicability to nonlinear…

Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically…

Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task. Despite growing interest, the literature on…

Scaling regression to large datasets is a common problem in many application areas. We propose a two step approach to scaling regression to large datasets. Using a regression tree (CART) to segment the large dataset constitutes the first…

Calibrating simulation models that take large quantities of multi-dimensional data as input is a hard simulation optimization problem. Existing adaptive sampling strategies offer a methodological solution. However, they may not sufficiently…

In this paper, we present a contraction-guided adaptive partitioning algorithm for improving interval-valued robust reachable set estimates in a nonlinear feedback loop with a neural network controller and disturbances. Based on an estimate…

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…

Instruction tuning is critical for adapting large language models (LLMs) to downstream tasks, and recent studies have demonstrated that small amounts of human-curated data can outperform larger datasets, challenging traditional data scaling…

In the world of big data, many people find it difficult to access the information they need quickly and accurately. In order to overcome this, research on the system that recommends information accurately to users is continuously conducted.…

Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This…

Recommender systems easily face the issue of user preference shifts. User representations will become out-of-date and lead to inappropriate recommendations if user preference has shifted over time. To solve the issue, existing work focuses…

Dataset distillation extracts a small set of synthetic training samples from a large dataset with the goal of achieving competitive performance on test data when trained on this sample. In this work, we tackle dataset distillation at its…

Training recommendation models on large datasets requires significant time and resources. It is desired to construct concise yet informative datasets for efficient training. Recent advances in dataset condensation show promise in addressing…

Predicting human motion in unstructured and dynamic environments is difficult as humans naturally exhibit complex behaviors that can change drastically from one environment to the next. In order to alleviate this issue, we propose to encode…

Service monitoring applications continuously produce data to monitor their availability. Hence, it is critical to classify incoming data in real-time and accurately. For this purpose, our study develops an adaptive classification approach…

For a fixed parameter size, the capabilities of large models are primarily determined by the quality and quantity of its training data. Consequently, training datasets now grow faster than the rate at which new data is indexed on the web,…

It is impossible today to pretend that the practice of machine learning is always compatible with the idea that training and testing data follow the same distribution. Several authors have recently used ensemble techniques to show how…

Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most methods collapse and perform worse than the original pretrained…