相关论文: Data-Efficient Training by Evolved Sampling

Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In this paper, we propose to learn a world…

In recent years, the data collected for artificial intelligence has grown to an unmanageable amount. Particularly within industrial applications, such as autonomous vehicles, model training computation budgets are being exceeded while model…

The ensemble of deep neural networks has been shown, both theoretically and empirically, to improve generalization accuracy on the unseen test set. However, the high training cost hinders its efficiency since we need a sufficient number of…

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss…

To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems. Similarly, a machine learning model…

Sparse portfolio optimization is a fundamental yet challenging problem in quantitative finance, since traditional approaches heavily relying on historical return statistics and static objectives can hardly adapt to dynamic market regimes.…

Although numerical weather forecasting methods have dominated the field, recent advances in deep learning methods, such as diffusion models, have shown promise in ensemble weather forecasting. However, such models are typically…

Feature selection is a crucial step in data mining to enhance model performance by reducing data dimensionality. However, the increasing dimensionality of collected data exacerbates the challenge known as the "curse of dimensionality",…

Humans are able to accelerate their learning by selecting training materials that are the most informative and at the appropriate level of difficulty. We propose a framework for distributing deep learning in which one set of workers search…

Spatio-temporal forecasting is fundamental to intelligent systems in transportation, climate science, and urban planning. However, training deep learning models on the massive, often redundant, datasets from these domains presents a…

Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world applications, as it aims to maximize long-term rewards while satisfying safety constraints. However, safe RL often suffers from sample inefficiency, requiring…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

A key challenge in the continual learning setting is to efficiently learn a sequence of tasks without forgetting how to perform previously learned tasks. Many existing approaches to this problem work by either retraining the model on…

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

With the rapid expansion of edge devices, such as IoT devices, where crucial data needed for machine learning applications is generated, it becomes essential to promote their participation in privacy-preserving Federated Learning (FL)…

In this era of big data, feature selection techniques, which have long been proven to simplify the model, makes the model more comprehensible, speed up the process of learning, have become more and more important. Among many developed…

Evolution strategy (ES) has been shown great promise in many challenging reinforcement learning (RL) tasks, rivaling other state-of-the-art deep RL methods. Yet, there are two limitations in the current ES practice that may hinder its…

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this white paper, we addressed the challenge of efficiently…

Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-importance criteria, i.e., deciding what to select, while…