相关论文: Inference Offloading for Cost-Sensitive Binary Cla…

Transfer learning is important for foundation models to adapt to downstream tasks. However, many foundation models are proprietary, so users must share their data with model owners to fine-tune the models, which is costly and raise privacy…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Classification imbalance arises when one class is much rarer than the other. We frame this setting as transfer learning under label (prior) shift between an imbalanced source distribution induced by the observed data and a balanced target…

Offline preference-based reinforcement learning (PbRL) provides an effective way to overcome the challenges of designing reward and the high costs of online interaction. However, since labeling preference needs real-time human feedback,…

Generative models such as diffusion have been employed as world models in offline reinforcement learning to generate synthetic data for more effective learning. Existing work either generates diffusion models one-time prior to training or…

Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distribution shifts. We…

This paper introduces a novel computational approach for offloading sensor data processing tasks to servers in edge networks for better accuracy and makespan. A task is assigned with one of several offloading options, each comprises a…

Off-Policy Estimation (OPE) methods allow us to learn and evaluate decision-making policies from logged data. This makes them an attractive choice for the offline evaluation of recommender systems, and several recent works have reported…

In this paper, we investigate the sample complexity of policy evaluation in infinite-horizon offline reinforcement learning (also known as the off-policy evaluation problem) with linear function approximation. We identify a hard regime…

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic…

Recent Offline Reinforcement Learning methods have succeeded in learning high-performance policies from fixed datasets of experience. A particularly effective approach learns to first identify and then mimic optimal decision-making…

The frequency-weighted model order reduction techniques are used to find a lower-order approximation of the high-order system that exhibits high-fidelity within the frequency region emphasized by the frequency weights. In this paper, we…

Active learning is a learning strategy whereby the machine learning algorithm actively identifies and labels data points to optimize its learning. This strategy is particularly effective in domains where an abundance of unlabeled data…

We consider the off-policy evaluation (OPE) problem in contextual bandits, where the goal is to estimate the value of a target policy using the data collected by a logging policy. Most popular approaches to the OPE are variants of the…

As a popular form of knowledge and experience, patterns and their identification have been critical tasks in most data mining applications. However, as far as we are aware, no study has systematically examined the dynamics of pattern values…

$\mathcal{H}_2$-optimal model order reduction algorithms represent a significant class of techniques, known for their accuracy, which has been extensively validated over the past two decades. Among these, the Iterative Rational Krylov…

As foundation models grow in size, fine-tuning them becomes increasingly expensive. While GPU spot instances offer a low-cost alternative to on-demand resources, their volatile prices and availability make deadline-aware scheduling…

Network datasets appear across a wide range of scientific fields, including biology, physics, and the social sciences. To enable data-driven discoveries from these networks, statistical inference techniques like estimation and hypothesis…

The abductive natural language inference task ($\alpha$NLI) is proposed to evaluate the abductive reasoning ability of a learning system. In the $\alpha$NLI task, two observations are given and the most plausible hypothesis is asked to pick…

Industrial systems increasingly depend on Machine Learning (ML), and operate on heterogeneous nodes that must satisfy tight latency, energy, and memory constraints. Dynamic ML models, which reconfigure their computational footprint at…