Related papers: Adaptive Ensemble Aggregation for Actor-Critics

In this work, we offer a theoretical analysis of two modern optimization techniques for training large and complex models: (i) adaptive optimization algorithms, such as Adam, and (ii) the model exponential moving average (EMA).…

The training and fine-tuning of large language models (LLMs) often involve diverse textual data from multiple sources, which poses challenges due to conflicting gradient directions, hindering optimization and specialization. These…

Actor-critic deep reinforcement learning (DRL) algorithms have recently achieved prominent success in tackling various challenging reinforcement learning (RL) problems, particularly complex control tasks with high-dimensional continuous…

While on-policy algorithms are known for their stability, they often demand a substantial number of samples. In contrast, off-policy algorithms, which leverage past experiences, are considered sample-efficient but tend to exhibit…

We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning. Supported by the new theory, arbitrary…

Integrating Artificial Intelligence (AI) into software systems has significantly enhanced their capabilities while escalating energy demands. Ensemble learning, combining predictions from multiple models to form a single prediction,…

A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as Embedded Ensembling (EE); its particular examples are…

Modeling correlated or highly stratified multiple-response data becomes a common data analysis task due to modern data monitoring facilities and methods. Generalized estimating equations (GEE) is one of the popular statistical methods for…

Detecting anomalies for multivariate time-series without manual supervision continues a challenging problem due to the increased scale of dimensions and complexity of today's IT monitoring systems. Recent progress of unsupervised…

In Domain Generalization (DG) settings, models trained independently on a given set of training domains have notoriously chaotic performance on distribution shifted test domains, and stochasticity in optimization (e.g. seed) plays a big…

The motivation of this work is to improve the performance of standard stacking approaches or ensembles, which are composed of simple, heterogeneous base models, through the integration of the generation and selection stages for regression…

Evolutionary algorithms (EAs), a large class of general purpose optimization algorithms inspired from the natural phenomena, are widely used in various industrial optimizations and often show excellent performance. This paper presents an…

Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection. However, neural networks are known to be vulnerable to overfitting, and therefore have limited potential in the unsupervised outlier…

Whether deterministic or stochastic, models can be viewed as functions designed to approximate a specific quantity of interest. We introduce Minimal Empirical Variance Aggregation (MEVA), a data-driven framework that integrates predictions…

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…

Action quality assessment (AQA) aims at automatically judging human action based on a video of the said action and assigning a performance score to it. The majority of works in the existing literature on AQA divide RGB videos into short…

Adversarial attacks have rendered high security risks on modern deep learning systems. Adversarial training can significantly enhance the robustness of neural network models by suppressing the non-robust features. However, the models often…

Empathic accuracy (EA) is the ability to accurately understand another person\textquotesingle s thoughts and feelings, which is crucial for social and psychological interactions. Traditionally, EA is assessed by comparing a…

Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending,…

Ensemble learning is a popular technique to improve the accuracy of machine learning models. It traditionally hinges on the rationale that aggregating multiple weak models can lead to better models with lower variance and hence higher…