Related papers: A Linear Time Natural Evolution Strategy for Non-S…

Natural-gradient descent (NGD) on structured parameter spaces (e.g., low-rank covariances) is computationally challenging due to difficult Fisher-matrix computations. We address this issue by using \emph{local-parameter coordinates} to…

An evolution strategy (ES) variant based on a simplification of a natural evolution strategy recently attracted attention because it performs surprisingly well in challenging deep reinforcement learning domains. It searches for neural…

Many scientific and technological problems are related to optimization. Among them, black-box optimization in high-dimensional space is particularly challenging. Recent neural network-based black-box optimization studies have shown…

For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries.Due to the costly stochastic…

This paper introduces Evolutionary Multi-Objective Network Architecture Search (EMNAS) for the first time to optimize neural network architectures in large-scale Reinforcement Learning (RL) for Autonomous Driving (AD). EMNAS uses genetic…

Inference-time scaling offers a versatile paradigm for aligning visual generative models with downstream objectives without parameter updates. However, existing approaches that optimize the high-dimensional initial noise suffer from severe…

Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically…

Time series forecasting (TSF) is one of the most important tasks in data science given the fact that accurate time series (TS) predictive models play a major role across a wide variety of domains including finance, transportation, health…

With the birth of the next-generation GPS III constellation and the upcoming launch of the Navigation Technology Satellite-3 (NTS-3) testing platform to explore future technologies for GPS, we are indeed entering a new era of satellite…

Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional…

Recurrent neural networks are good at solving prediction problems. However, finding a network that suits a problem is quite hard because their performance is strongly affected by their architecture configuration. Automatic architecture…

Evolutionary algorithms (EAs) have been successfully applied to optimize the policies for Reinforcement Learning (RL) tasks due to their exploration ability. The recently proposed Negatively Correlated Search (NCS) provides a distinct…

In recent years, Evolutionary Strategies were actively explored in robotic tasks for policy search as they provide a simpler alternative to reinforcement learning algorithms. However, this class of algorithms is often claimed to be…

The performance of a deep neural network is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary neural architecture…

Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several…

Evolutionary Strategies (ES) are known to be an effective black-box optimization technique for deep neural networks when the true gradients cannot be computed, such as in Reinforcement Learning. We continue a recent line of research that…

K-nearest neighbor (kNN) search has wide applications in many areas, including data mining, machine learning, statistics and many applied domains. Inspired by the success of ensemble methods and the flexibility of tree-based methodology, we…

Neural Architecture Search (NAS) is an important yet challenging task in network design due to its high computational consumption. To address this issue, we propose the Reinforced Evolutionary Neural Architecture Search (RE- NAS), which is…

For many years, Evolutionary Algorithms (EAs) have been applied to improve Neural Networks (NNs) architectures. They have been used for solving different problems, such as training the networks (adjusting the weights), designing network…

Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep neural networks roughly as well as Q-learning and policy gradient methods on challenging deep reinforcement learning (RL) problems, but are much…