Search for: All records

Abstract First-order optimization methods tend to inherently favor certain solutions over others when minimizing an underdetermined training objective that has multiple global optima. This phenomenon, known asimplicit bias, plays a critical role in understanding the generalization capabilities of optimization algorithms. Recent research has revealed that in separable binary classification tasks gradient-descent-based methods exhibit an implicit bias for the$$\ell _2$$ ${\ell }_2$-maximal margin classifier. Similarly, generic optimization methods, such as mirror descent and steepest descent, have been shown to converge to maximal margin classifiers defined by alternative geometries. While gradient-descent-based algorithms provably achievefastimplicit bias rates, corresponding rates in the literature for generic optimization methods are relatively slow. To address this limitation, we present a series of state-of-the-art implicit bias rates for mirror descent and steepest descent algorithms. Our primary technique involves transforming a generic optimization algorithm into an online optimization dynamic that solves a regularized bilinear game, providing a unified framework for analyzing the implicit bias of various optimization methods. Our accelerated rates are derived by leveraging the regret bounds of online learning algorithms within this game framework. We then show the flexibility of this framework by analyzing the implicit bias inadversarial training, and again obtain significantly improved convergence rates. 

Abstract Aphid infestation poses a significant threat to crop production, rural communities, and global food security. While chemical pest control is crucial for maximizing yields, applying chemicals across entire fields is both environmentally unsustainable and costly. Hence, precise localization and management of aphids are essential for targeted pesticide application. The paper primarily focuses on using deep learning models for detecting aphid clusters. We propose a novel approach for estimating infection levels by detecting aphid clusters. To facilitate this research, we have captured a large-scale dataset from sorghum fields, manually selected 5447 images containing aphids, and annotated each individual aphid cluster within these images. To facilitate the use of machine learning models, we further process the images by cropping them into patches, resulting in a labeled dataset comprising 151,380 image patches. Then, we implemented and compared the performance of four state-of-the-art object detection models (VFNet, GFLV2, PAA, and ATSS) on the aphid dataset. Extensive experimental results show that all models yield stable similar performance in terms of average precision and recall. We then propose to merge close neighboring clusters and remove tiny clusters caused by cropping, and the performance is further boosted by around 17%. The study demonstrates the feasibility of automatically detecting and managing insects using machine learning models. The labeled dataset will be made openly available to the research community. 

Abstract Autophagy, as an intracellular degradation system, plays a critical role in plant immunity. However, the involvement of autophagy in the plant immune system and its function in plant nematode resistance are largely unknown. Here, we show that root-knot nematode (RKN;Meloidogyne incognita) infection induces autophagy in tomato (Solanum lycopersicum) and differentatgmutants exhibit high sensitivity to RKNs. The jasmonate (JA) signaling negative regulators JASMONATE-ASSOCIATED MYC2-LIKE 1 (JAM1), JAM2 and JAM3 interact with ATG8s via an ATG8-interacting motif (AIM), and JAM1 is degraded by autophagy during RKN infection. JAM1 impairs the formation of a transcriptional activation complex between ETHYLENE RESPONSE FACTOR 1 (ERF1) and MEDIATOR 25 (MED25) and interferes with transcriptional regulation of JA-mediated defense-related genes by ERF1. Furthermore, ERF1 acts in a positive feedback loop and regulates autophagy activity by transcriptionally activatingATGexpression in response to RKN infection. Therefore, autophagy promotes JA-mediated defense against RKNs via forming a positive feedback circuit in the degradation of JAMs and transcriptional activation by ERF1.